{"task":"Use hunt-cache-poison","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"feedback":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","outcome_api":"https://www.openagentskill.com/api/agent/outcome","method":"POST","selected_skill_slug":"zilliztech-gptcache","selected_skill_name":"GPTCache","alternative_skill_slugs":["elementalsouls-hunt-cache-poison","cnighswonger-claude-code-cache-fix","hackmanit-web-cache-vulnerability-scanner","ali-vilab-teacache"],"expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"report_after":["After trying the selected skill, report whether it solved the task.","Mark blocked_by_risk when audit, license, credentials, shell, or network risk prevents safe use.","Mark setup_required when the skill looks relevant but needs missing keys, data, or manual configuration.","Mark not_relevant when the selected skill does not match the task after inspection.","Include output_quality, error_type, workspace, human_review_required, evidence_url, and time_to_useful_ms when available."],"json_example":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","skill_slug":"zilliztech-gptcache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5\" --skill \"zilliztech-gptcache\" --task \"Use hunt-cache-poison\" --agent \"codex\" --outcome success"},"agent_feedback_loop":{"version":"openagentskill-agent-feedback-loop-v3","status":"active","purpose":"Report the result of one resolved skill run so Trust Score v5 and future Resolve rankings learn from real use.","event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","selected_skill_slug":"zilliztech-gptcache","selected_skill_name":"GPTCache","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","idempotency":"Retrying the same event_id updates the previous outcome.","dry_run":{"supported":true,"instruction":"Set dry_run=true to validate a payload before wiring a new agent integration."},"expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"error_types":["install_failed","runtime_error","not_relevant","permission_blocked","risk_blocked","setup_required","low_quality_output","missing_dependency","timeout","other"],"workspaces":["sandbox","local","ci","production","unknown"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url"],"payload_template":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","skill_slug":"zilliztech-gptcache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5\" --skill \"zilliztech-gptcache\" --task \"Use hunt-cache-poison\" --agent \"codex\" --outcome success","ranking_inputs_updated":["Trust Score v5 outcome confidence","Resolve ranking outcome evidence","Skill detail outcome signal block","Outcome leaderboard"]},"install_receipt":{"version":"openagentskill-install-receipt-v2","receipt_id":"receipt_01af834b-cbf7-45d6-9db1-075f463f40a5","resolve_event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","generated_at":"2026-09-05T09:44:32.958Z","task":"Use hunt-cache-poison","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"urls":{"web":"https://www.openagentskill.com/resolve?task=Use+hunt-cache-poison&agent=codex&max_risk=medium","json":"https://www.openagentskill.com/api/agent/receipt?task=Use+hunt-cache-poison&agent=codex&max_risk=medium","text":"https://www.openagentskill.com/api/agent/receipt?task=Use+hunt-cache-poison&agent=codex&max_risk=medium&format=text","resolve_json":"https://www.openagentskill.com/api/agent/resolve?task=Use+hunt-cache-poison&agent=codex&max_risk=medium","resolve_text":"https://www.openagentskill.com/api/agent/resolve?task=Use+hunt-cache-poison&agent=codex&max_risk=medium&format=text"},"selected_skill":{"slug":"zilliztech-gptcache","name":"GPTCache","description":"Semantic cache for LLMs. Fully integrated with LangChain and llama_index. ","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/zilliztech-gptcache","api_url":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache","audit_url":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium","install_api_url":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install","repository":"https://github.com/zilliztech/GPTCache","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"install":{"command":"npx skills add zilliztech/GPTCache","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"GPTCache\" agent skill from https://github.com/zilliztech/GPTCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","ready":true,"policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"blocked":false},"decision":{"recommendation":"Require human approval before installing into a real workspace.","why_selected":["Matches task terms: cache","Useful GitHub adoption: 8,067 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30","Companion skill for RAG and knowledge","71/100 Trust Score","0/100 Agent Proven Score"],"suited_tasks":["RAG and knowledge workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","LangChain"]},"trust":{"score":71,"label":"Sandbox only","version":"trust-score-v5","base_score":79,"outcome_confidence":0,"outcome_signal":"No agent outcome data yet","outcome_total":0,"outcome_success_rate":null,"decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["71/100 Trust Score v5","79/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]}},"agent_proven":{"score":0,"label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"installAttempts":0,"installSuccessRate":null,"riskBlocked":0,"setupRequired":0,"avgOutputQuality":null,"productionOutcomes":0}},"risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety_score":62,"audit_score":74,"notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push","62/100 agent safety score"],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 74/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"elementalsouls-hunt-cache-poison","name":"hunt-cache-poison","url":"https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison","audit_url":"https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison/audit","install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","trust_score":68,"audit_score":81,"safety_score":57,"reason":"Matches task terms: hunt, cache, poison","policy":"review"},{"slug":"cnighswonger-claude-code-cache-fix","name":"Claude Code Cache Fix","url":"https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix","audit_url":"https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix/audit","install_command":"npx skills add cnighswonger/claude-code-cache-fix","trust_score":70,"audit_score":74,"safety_score":50,"reason":"Matches task terms: cache","policy":"review"},{"slug":"hackmanit-web-cache-vulnerability-scanner","name":"Web Cache Vulnerability Scanner","url":"https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner","audit_url":"https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner/audit","install_command":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","trust_score":79,"audit_score":78,"safety_score":54,"reason":"Matches task terms: cache","policy":"review"},{"slug":"ali-vilab-teacache","name":"TeaCache","url":"https://www.openagentskill.com/skills/ali-vilab-teacache","audit_url":"https://www.openagentskill.com/skills/ali-vilab-teacache/audit","install_command":"npx skills add ali-vilab/TeaCache","trust_score":79,"audit_score":72,"safety_score":60,"reason":"Matches task terms: cache","policy":"review"}],"outcome_feedback":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","skill_slug":"zilliztech-gptcache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"dry_run_payload":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","skill_slug":"zilliztech-gptcache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"},"dry_run":true},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5\" --skill \"zilliztech-gptcache\" --task \"Use hunt-cache-poison\" --agent \"codex\" --outcome success","instruction":"After one narrow sandbox run, report success, failed, not_relevant, blocked_by_risk, or setup_required so Trust Score v5 and future agent rankings learn from real usage."},"next_steps":["Read the audit page: https://www.openagentskill.com/skills/zilliztech-gptcache/audit","Fetch the pre-install eval: https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium","Do not auto-install yet. Ask for human review before running: npx skills add zilliztech/GPTCache","Run one narrow task with no production secrets or irreversible side effects.","Report the result to https://www.openagentskill.com/api/agent/outcome using event_id resolve_01af834b-cbf7-45d6-9db1-075f463f40a5."],"stable_fields":["receipt_id","selected_skill","install","trust","risk","alternatives","outcome_feedback","next_steps"],"freshness_policy":"Re-resolve before production use or after 24 hours to refresh trust, audit, and outcome signals."},"recommendation":{"task":"Use hunt-cache-poison","agent":"codex","best_skill":{"slug":"zilliztech-gptcache","name":"GPTCache","description":"Semantic cache for LLMs. Fully integrated with LangChain and llama_index. ","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/zilliztech-gptcache","api_url":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache","audit_url":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium","repository":"https://github.com/zilliztech/GPTCache","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"install":{"command":"npx skills add zilliztech/GPTCache","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"GPTCache\" agent skill from https://github.com/zilliztech/GPTCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","install_api":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install","ready":true,"review_required":true,"auto_install_allowed":false,"policy":"review"},"why_recommended":["Matches task terms: cache","Useful GitHub adoption: 8,067 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30","Companion skill for RAG and knowledge","71/100 OpenAgentSkill Trust Score v5","74/100 audit score"],"trust_score_v5":{"score":71,"base_score":79,"outcome_confidence":0,"tier":"review","label":"Sandbox only","version":"trust-score-v5","install_policy":"human_review_before_install","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["71/100 Trust Score v5","79/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"evidence":{"stars":"8.1K GitHub stars","repoActivity":"8.1K stars, 583 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/zilliztech/GPTCache","install":"npx skills add zilliztech/GPTCache","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"agent_compatibility":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomes":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add zilliztech/GPTCache","trust_score":71,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"best_for":["rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"],"do_not_use_for":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":79,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"trust_score_v4":{"score":79,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"8.1K GitHub stars","repoActivity":"8.1K stars, 583 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/zilliztech/GPTCache","install":"npx skills add zilliztech/GPTCache","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"agent_compatibility":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomes":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"],"do_not_use_for":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_score_v3":{"score":79,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"8.1K GitHub stars","repoActivity":"8.1K stars, 583 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/zilliztech/GPTCache","install":"npx skills add zilliztech/GPTCache","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"agent_compatibility":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},"trust_score_v2":{"score":79,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"8.1K GitHub stars","repoActivity":"8.1K stars, 583 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/zilliztech/GPTCache","install":"npx skills add zilliztech/GPTCache","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"agent_compatibility":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},"risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"62/100 Review before install","trust":"79/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","62/100 agent safety score"]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"zilliztech-gptcache","name":"GPTCache","description":"Semantic cache for LLMs. Fully integrated with LangChain and llama_index. ","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/zilliztech-gptcache","repository":"https://github.com/zilliztech/GPTCache","github_repo":"zilliztech/GPTCache"},"suited_tasks":["RAG and knowledge workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","LangChain"],"install":{"command":"npx skills add zilliztech/GPTCache","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add zilliztech-gptcache"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"GPTCache\" agent skill from https://github.com/zilliztech/GPTCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"GPTCache\" as a Claude Code skill from https://github.com/zilliztech/GPTCache. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"GPTCache\" from https://github.com/zilliztech/GPTCache into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zilliztech-gptcache"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"8.1K GitHub stars","repoActivity":"8.1K stars, 583 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/zilliztech/GPTCache","install":"npx skills add zilliztech/GPTCache","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":74,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"agent_contract":{"task_input":"Use hunt-cache-poison","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 74/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zilliztech-gptcache (GPTCache)","install_command":"npx skills add zilliztech/GPTCache","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"zilliztech-gptcache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/zilliztech-gptcache","api":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache","audit":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zilliztech-gptcache"}},"agent_contract":{"version":"openagentskill-resolve-contract-v2","input_task":"Use hunt-cache-poison","recommended_skill_slug":"zilliztech-gptcache","recommended_skill_name":"GPTCache","install_command":"npx skills add zilliztech/GPTCache","install_policy":"review","auto_install_allowed":false,"human_review_required":true,"audit_url":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium","skill_api_url":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache","do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 74/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zilliztech-gptcache (GPTCache)","install_command":"npx skills add zilliztech/GPTCache","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"supply_asset":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"research-agents","title":"Research agents"},{"slug":"customer-support","title":"Customer support"}]},"maintenance":{"status":"stale","label":"1y since push","daysSincePush":421,"lastPushedAt":"2025-07-11T09:04:36+00:00"},"github_quality":{"stars":8067,"starsLabel":"8.1K","forks":583,"license":"MIT","qualityScore":74,"trustScore":79,"auditScore":74},"coverage_tags":["Research","RAG and knowledge","rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"]},"alternatives":[{"slug":"elementalsouls-hunt-cache-poison","name":"hunt-cache-poison","url":"https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison","install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","trust_score":68,"audit_score":81,"safety_score":57,"why_consider":"Matches task terms: hunt, cache, poison","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"57/100 Review before install","trust":"68/100 Manual review","notes":["High-risk permission hints: Secrets or environment access","Permission surface may require sandboxing","SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Description mentions 10 public bug bounty reports but report_count is 8 - inconsistency.","No explicit statement about only testing on authorized targets, though implied by bug bounty context."]}},{"slug":"cnighswonger-claude-code-cache-fix","name":"Claude Code Cache Fix","url":"https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix","install_command":"npx skills add cnighswonger/claude-code-cache-fix","trust_score":70,"audit_score":74,"safety_score":50,"why_consider":"Matches task terms: cache","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"50/100 Avoid automatic install","trust":"70/100 Manual review","notes":["High-risk permission hints: Shell or command execution","License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata"]}},{"slug":"hackmanit-web-cache-vulnerability-scanner","name":"Web Cache Vulnerability Scanner","url":"https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner","install_command":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","trust_score":79,"audit_score":78,"safety_score":54,"why_consider":"Matches task terms: cache","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"54/100 Avoid automatic install","trust":"79/100 Strong shortlist","notes":["High-risk permission hints: Shell or command execution","Quality score needs review","Documentation summary is thin"]}},{"slug":"ali-vilab-teacache","name":"TeaCache","url":"https://www.openagentskill.com/skills/ali-vilab-teacache","install_command":"npx skills add ali-vilab/TeaCache","trust_score":79,"audit_score":72,"safety_score":60,"why_consider":"Matches task terms: cache","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"60/100 Review before install","trust":"79/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]}}],"decision_packet":{"version":"openagentskill-agent-decision-packet-v1","task":"Use hunt-cache-poison","agent":"codex","selected_skill":{"slug":"zilliztech-gptcache","name":"GPTCache","url":"https://www.openagentskill.com/skills/zilliztech-gptcache","api_url":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache","audit_url":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit","repository":"https://github.com/zilliztech/GPTCache","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"suited_tasks":["RAG and knowledge workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","LangChain"],"install":{"command":"npx skills add zilliztech/GPTCache","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":71,"label":"Sandbox only","version":"trust-score-v5","base_score":79,"outcome_confidence":0,"decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["71/100 Trust Score v5","79/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"status":"pass","detail":"8.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"status":"pass","detail":"8.1K stars, 583 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"status":"pass","detail":"npx skills add zilliztech/GPTCache"},{"id":"install_safety","label":"Install command safety","score":92,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"status":"pass","detail":"https://github.com/zilliztech/GPTCache"},{"id":"review_status","label":"Review status","score":88,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"status":"info","detail":"No agent outcome data yet"}]},"risk":{"level":"Needs review","audit_label":"Needs review","safety":"62/100 Review before install","trust":"79/100 Strong shortlist","safety_tier":"Reviewed with permission notes","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 74/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"elementalsouls-hunt-cache-poison","name":"hunt-cache-poison","url":"https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison","install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","trust_score":68,"audit_score":81,"safety_score":57,"why_consider":"Matches task terms: hunt, cache, poison","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"57/100 Review before install","trust":"68/100 Manual review","notes":["High-risk permission hints: Secrets or environment access","Permission surface may require sandboxing","SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Description mentions 10 public bug bounty reports but report_count is 8 - inconsistency.","No explicit statement about only testing on authorized targets, though implied by bug bounty context."]}},{"slug":"cnighswonger-claude-code-cache-fix","name":"Claude Code Cache Fix","url":"https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix","install_command":"npx skills add cnighswonger/claude-code-cache-fix","trust_score":70,"audit_score":74,"safety_score":50,"why_consider":"Matches task terms: cache","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"50/100 Avoid automatic install","trust":"70/100 Manual review","notes":["High-risk permission hints: Shell or command execution","License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata"]}},{"slug":"hackmanit-web-cache-vulnerability-scanner","name":"Web Cache Vulnerability Scanner","url":"https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner","install_command":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","trust_score":79,"audit_score":78,"safety_score":54,"why_consider":"Matches task terms: cache","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"54/100 Avoid automatic install","trust":"79/100 Strong shortlist","notes":["High-risk permission hints: Shell or command execution","Quality score needs review","Documentation summary is thin"]}},{"slug":"ali-vilab-teacache","name":"TeaCache","url":"https://www.openagentskill.com/skills/ali-vilab-teacache","install_command":"npx skills add ali-vilab/TeaCache","trust_score":79,"audit_score":72,"safety_score":60,"why_consider":"Matches task terms: cache","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"60/100 Review before install","trust":"79/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]}}],"outcome_feedback":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","skill_slug":"zilliztech-gptcache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5\" --skill \"zilliztech-gptcache\" --task \"Use hunt-cache-poison\" --agent \"codex\" --outcome success"},"next_agent_action":"Ask for human approval or choose a safer alternative before installing.","stable_fields":["decision_packet.selected_skill","decision_packet.install","decision_packet.risk.do_not_use_when","decision_packet.alternatives","decision_packet.outcome_feedback","decision_packet.trust.decision"]},"agent_instruction":"Use GPTCache for: Use hunt-cache-poison\nReview audit: https://www.openagentskill.com/skills/zilliztech-gptcache/audit\nAsk for human approval before installing: npx skills add zilliztech/GPTCache\nIf the audit or policy warnings are unacceptable, choose one of the alternatives."},"recommendation_lanes":{"best_match":{"rank":4,"match_score":30,"raw_match_score":103,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"zilliztech-gptcache","name":"GPTCache","description":"Semantic cache for LLMs. Fully integrated with LangChain and llama_index. ","category":"rag-knowledge","github_stars":8067,"created_at":"2026-06-05T06:01:49.808031+00:00","updated_at":"2025-07-11T09:04:36+00:00","repository":"https://github.com/zilliztech/GPTCache","github_repo":"zilliztech/GPTCache","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: cache","Useful GitHub adoption: 8,067 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"research-agents","title":"Research agents"},{"slug":"customer-support","title":"Customer support"}]},"applicableAgents":["OpenAI Agents","LangChain","CLI","Codex","Claude Code"],"install":{"ready":true,"command":"npx skills add zilliztech/GPTCache","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":8067,"starsLabel":"8.1K","forks":583,"license":"MIT","qualityScore":74,"trustScore":79,"auditScore":74},"maintenance":{"status":"stale","label":"1y since push","daysSincePush":421,"lastPushedAt":"2025-07-11T09:04:36+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"coverageTags":["Research","RAG and knowledge","rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"]},"quality":{"score":74,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"8.1K","tone":"positive"},{"label":"Freshness","value":"1y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":79,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"8.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"8.1K stars, 583 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add zilliztech/GPTCache"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/zilliztech/GPTCache"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"8.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"8.1K stars, 583 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add zilliztech/GPTCache"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/zilliztech/GPTCache"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"OpenAgentSkill usage","detail":"6 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"8.1K GitHub stars","repoActivity":"8.1K stars, 583 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/zilliztech/GPTCache","install":"npx skills add zilliztech/GPTCache","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add zilliztech/GPTCache","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","1y since push"]},"agentCompatibility":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":71,"base_score":79,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["71/100 Trust Score v5","79/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"8.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"8.1K stars, 583 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add zilliztech/GPTCache"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/zilliztech/GPTCache"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"8.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"8.1K stars, 583 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add zilliztech/GPTCache"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/zilliztech/GPTCache"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"OpenAgentSkill usage","detail":"6 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"8.1K GitHub stars","repoActivity":"8.1K stars, 583 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/zilliztech/GPTCache","install":"npx skills add zilliztech/GPTCache","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add zilliztech/GPTCache","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","1y since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add zilliztech/GPTCache","trust_score":71,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":79,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"safety":{"score":62,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","62/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","62/100 agent safety score"]},"decision":{"readiness_score":79,"readiness_label":"Strong shortlist","headline":"Companion skill for RAG and knowledge","role":"Companion skill","best_for":["RAG and knowledge workflows","OpenAI Agents teams","teams that value GitHub adoption signals"],"risks":["Repository looks stale"],"next_steps":["Install it in a sandbox agent and run one RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add zilliztech/GPTCache","value":"Install the \"GPTCache\" agent skill from https://github.com/zilliztech/GPTCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review GPTCache trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add zilliztech-gptcache","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"GPTCache\" agent skill from https://github.com/zilliztech/GPTCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"GPTCache\" as a Claude Code skill from https://github.com/zilliztech/GPTCache. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"GPTCache\" from https://github.com/zilliztech/GPTCache into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"zilliztech-gptcache","name":"GPTCache","description":"Semantic cache for LLMs. Fully integrated with LangChain and llama_index. ","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/zilliztech-gptcache","repository":"https://github.com/zilliztech/GPTCache","github_repo":"zilliztech/GPTCache"},"suited_tasks":["RAG and knowledge workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","LangChain"],"install":{"command":"npx skills add zilliztech/GPTCache","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add zilliztech-gptcache"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"GPTCache\" agent skill from https://github.com/zilliztech/GPTCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"GPTCache\" as a Claude Code skill from https://github.com/zilliztech/GPTCache. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"GPTCache\" from https://github.com/zilliztech/GPTCache into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zilliztech-gptcache"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"8.1K GitHub stars","repoActivity":"8.1K stars, 583 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/zilliztech/GPTCache","install":"npx skills add zilliztech/GPTCache","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":74,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"agent_contract":{"task_input":"Use hunt-cache-poison","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 74/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zilliztech-gptcache (GPTCache)","install_command":"npx skills add zilliztech/GPTCache","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"zilliztech-gptcache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/zilliztech-gptcache","api":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache","audit":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zilliztech-gptcache"}},"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"customer-support","title":"Customer support","url":"https://www.openagentskill.com/use-cases/customer-support"}],"urls":{"web":"https://www.openagentskill.com/skills/zilliztech-gptcache","api":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache","install_api":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install","audit":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/zilliztech-gptcache?metric=audit","repository":"https://github.com/zilliztech/GPTCache"}},"safer_alternative":{"rank":8,"match_score":30,"raw_match_score":94.2,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"elementalsouls-hunt-aspnet","name":"hunt-aspnet","description":"Hunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser MAC-bypass anti-pattern, request-validator bypass, trace.axd/elmah.axd disclosure, load-balanced ViewState cross-node failures, SafeControl enumeration via reflection, customErrors mode=Off stack-trace leaks, classic Webforms .aspx/.asmx/.svc surface. Built for ASP.NET Webforms + WCF + SharePoint farms.","category":"research","github_stars":4098,"created_at":"2026-09-02T16:41:07.90466+00:00","updated_at":"2026-09-02T08:49:05+00:00","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet","github_repo":"elementalsouls/Claude-BugHunter","source_version":{"version":"1.0.0","commit_sha":"0efc24c3510d55bfef117d5594c0766df14f887b","content_hash":"1606594f88ee4e178ab61ece133e83c53db64733da838aa7bc016c9daa5f9755","ref":"main","path":"skills/hunt-aspnet/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: hunt","Useful GitHub adoption: 4,098 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"research-agents","title":"Research agents"},{"slug":"document-processing","title":"Document processing"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":4098,"starsLabel":"4.1K","forks":637,"license":"MIT","qualityScore":83,"trustScore":82,"auditScore":87},"maintenance":{"status":"fresh","label":"3d since push","daysSincePush":3,"lastPushedAt":"2026-09-02T08:49:05+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","Research agents","agent-skill"]},"quality":{"score":83,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"4.1K","tone":"positive"},{"label":"Freshness","value":"3d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":82,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.1K stars, 637 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.1K stars, 637 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 637 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":74,"base_score":82,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["74/100 Trust Score v5","82/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.1K stars, 637 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.1K stars, 637 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 637 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet","trust_score":74,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":82,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":75,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","75/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","75/100 agent safety score"]},"decision":{"readiness_score":94,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","best_for":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet","value":"Install the \"hunt-aspnet\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser MAC-bypass anti-pattern, request-validator bypass, trace.axd/elmah.axd disclosure, load-balanced ViewState cross-node failures, SafeControl enumeration via reflection, customErrors mode=Off stack-trace leaks, classic Webforms .aspx/.asmx/.svc surface. Built for ASP.NET Webforms + WCF + SharePoint farms. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-aspnet\",\"task\":\"Install hunt-aspnet\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review hunt-aspnet trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add elementalsouls-hunt-aspnet","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"hunt-aspnet\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser MAC-bypass anti-pattern, request-validator bypass, trace.axd/elmah.axd disclosure, load-balanced ViewState cross-node failures, SafeControl enumeration via reflection, customErrors mode=Off stack-trace leaks, classic Webforms .aspx/.asmx/.svc surface. Built for ASP.NET Webforms + WCF + SharePoint farms. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-aspnet\",\"task\":\"Install hunt-aspnet\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"hunt-aspnet\" as a Claude Code skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Hunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser MAC-bypass anti-pattern, request-validator bypass, trace.axd/elmah.axd disclosure, load-balanced ViewState cross-node failures, SafeControl enumeration via reflection, customErrors mode=Off stack-trace leaks, classic Webforms .aspx/.asmx/.svc surface. Built for ASP.NET Webforms + WCF + SharePoint farms. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-aspnet\",\"task\":\"Install hunt-aspnet\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"hunt-aspnet\" from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Hunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser MAC-bypass anti-pattern, request-validator bypass, trace.axd/elmah.axd disclosure, load-balanced ViewState cross-node failures, SafeControl enumeration via reflection, customErrors mode=Off stack-trace leaks, classic Webforms .aspx/.asmx/.svc surface. Built for ASP.NET Webforms + WCF + SharePoint farms. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-aspnet\",\"task\":\"Install hunt-aspnet\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"elementalsouls-hunt-aspnet","name":"hunt-aspnet","description":"Hunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser MAC-bypass anti-pattern, request-validator bypass, trace.axd/elmah.axd disclosure, load-balanced ViewState cross-node failures, SafeControl enumeration via reflection, customErrors mode=Off stack-trace leaks, classic Webforms .aspx/.asmx/.svc surface. Built for ASP.NET Webforms + WCF + SharePoint farms.","category":"research","url":"https://www.openagentskill.com/skills/elementalsouls-hunt-aspnet","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet","github_repo":"elementalsouls/Claude-BugHunter"},"suited_tasks":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Search sources","Extract claims"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add elementalsouls-hunt-aspnet"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"hunt-aspnet\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser MAC-bypass anti-pattern, request-validator bypass, trace.axd/elmah.axd disclosure, load-balanced ViewState cross-node failures, SafeControl enumeration via reflection, customErrors mode=Off stack-trace leaks, classic Webforms .aspx/.asmx/.svc surface. Built for ASP.NET Webforms + WCF + SharePoint farms. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-aspnet\",\"task\":\"Install hunt-aspnet\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"hunt-aspnet\" as a Claude Code skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Hunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser MAC-bypass anti-pattern, request-validator bypass, trace.axd/elmah.axd disclosure, load-balanced ViewState cross-node failures, SafeControl enumeration via reflection, customErrors mode=Off stack-trace leaks, classic Webforms .aspx/.asmx/.svc surface. Built for ASP.NET Webforms + WCF + SharePoint farms. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-aspnet\",\"task\":\"Install hunt-aspnet\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"hunt-aspnet\" from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Hunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser MAC-bypass anti-pattern, request-validator bypass, trace.axd/elmah.axd disclosure, load-balanced ViewState cross-node failures, SafeControl enumeration via reflection, customErrors mode=Off stack-trace leaks, classic Webforms .aspx/.asmx/.svc surface. Built for ASP.NET Webforms + WCF + SharePoint farms. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-aspnet\",\"task\":\"Install hunt-aspnet\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-aspnet/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/elementalsouls-hunt-aspnet"},"trust":{"score":82,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 637 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":83,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"3d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use hunt-cache-poison","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 82/100 Strong shortlist","Audit: 87/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"elementalsouls-hunt-aspnet (hunt-aspnet)","install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-aspnet","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"elementalsouls-hunt-aspnet","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/elementalsouls-hunt-aspnet","api":"https://www.openagentskill.com/api/agent/skills/elementalsouls-hunt-aspnet","audit":"https://www.openagentskill.com/skills/elementalsouls-hunt-aspnet/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=elementalsouls-hunt-aspnet&task=Use%20hunt-cache-poison&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-aspnet/install","manifest":"https://www.openagentskill.com/api/registry/manifest/elementalsouls-hunt-aspnet"}},"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"}],"urls":{"web":"https://www.openagentskill.com/skills/elementalsouls-hunt-aspnet","api":"https://www.openagentskill.com/api/agent/skills/elementalsouls-hunt-aspnet","install_api":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-aspnet/install","audit":"https://www.openagentskill.com/skills/elementalsouls-hunt-aspnet/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=elementalsouls-hunt-aspnet&task=Use%20hunt-cache-poison&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/elementalsouls-hunt-aspnet?metric=audit","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-aspnet"}},"popular_alternative":{"rank":7,"match_score":30,"raw_match_score":94.3,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"elementalsouls-hunt-ato","name":"hunt-ato","description":"Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session fixation, (6) JWT manipulation (forge token to another identity; crypto details → hunt-jwt-crypto), (7) password change without step-up (chain with login timing/length oracle), (8) social-recovery / security-question brute-force, (9) SSO subdomain takeover at OAuth redirect_uri. Chains: cookie theft + password oracle + no step-up = persistent ATO; lax redirect_uri = auth-code theft; dangling-CNAME takeover at redirect_uri = ATO. Validate: demonstrate real takeover of test account B from attacker A's session; OOB/Collaborator confirm blind token-leak steps. Use when hunting ATO chains, testing password reset / email change / MFA / OAuth / session / JWT, or chaining primitives t","category":"security","github_stars":4098,"created_at":"2026-09-02T16:31:10.939035+00:00","updated_at":"2026-09-02T08:49:05+00:00","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato","github_repo":"elementalsouls/Claude-BugHunter","source_version":{"version":"1.0.0","commit_sha":"0efc24c3510d55bfef117d5594c0766df14f887b","content_hash":"f2afcab5682c117c77259b1ead3eb746aeefaa70c07c019b581b79ede09c7596","ref":"main","path":"skills/hunt-ato/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: hunt","Useful GitHub adoption: 4,098 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Testing and QA","description":"I need my agent to test a web app, reproduce bugs, and verify fixes.","useCases":[{"slug":"testing-qa","title":"Testing and QA"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":4098,"starsLabel":"4.1K","forks":637,"license":"MIT","qualityScore":83,"trustScore":72,"auditScore":82},"maintenance":{"status":"fresh","label":"3d since push","daysSincePush":3,"lastPushedAt":"2026-09-02T08:49:05+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Financial research output is not financial advice; require human review before any live investment decision","No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers.","Some paths (e.g., JWT manipulation) reference external skills (hunt-jwt-crypto) without linking them, which may require additional context.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"coverageTags":["Coding","Testing and QA","security","agent-skill"]},"quality":{"score":83,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"4.1K","tone":"positive"},{"label":"Freshness","value":"3d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers."]},"trust":{"version":"trust-score-v4","score":72,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.1K stars, 637 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":74,"weight":0.07,"status":"info","detail":"secrets or environment access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.1K stars, 637 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"secrets or environment access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 637 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push","Financial domain: human review is required before use in a live investment workflow."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["security","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":64,"base_score":72,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["64/100 Trust Score v5","72/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.1K stars, 637 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":74,"weight":0.07,"status":"info","detail":"secrets or environment access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.1K stars, 637 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"secrets or environment access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 637 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push","Financial domain: human review is required before use in a live investment workflow.","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["security","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato","trust_score":64,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["security","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":72,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":82,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Financial research output is not financial advice; require human review before any live investment decision","No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers.","Some paths (e.g., JWT manipulation) reference external skills (hunt-jwt-crypto) without linking them, which may require additional context.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"safety":{"score":58,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["High-risk permission hints: Secrets or environment access","58/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"secrets","label":"Secrets or environment access","reason":"Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.","severity":"high"}],"policy_warnings":["High-risk permission hints: Secrets or environment access","Financial research output is not financial advice; require human review before any live investment decision"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["High-risk permission hints: Secrets or environment access","58/100 agent safety score"]},"decision":{"readiness_score":94,"readiness_label":"Production-ready","headline":"Primary pick for Testing and QA","role":"Primary pick","best_for":["Testing and QA workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers.","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Testing and QA task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato","value":"Install the \"hunt-ato\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session fixation, (6) JWT manipulation (forge token to another identity; crypto details → hunt-jwt-crypto), (7) password change without step-up (chain with login timing/length oracle), (8) social-recovery / security-question brute-force, (9) SSO subdomain takeover at OAuth redirect_uri. Chains: cookie theft + password oracle + no step-up = persistent ATO; lax redirect_uri = auth-code theft; dangling-CNAME takeover at redirect_uri = ATO. Validate: demonstrate real takeover of test account B from attacker A's session; OOB/Collaborator confirm blind token-leak steps. Use when hunting ATO chains, testing password reset / email change / MFA / OAuth / session / JWT, or chaining primitives t After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-ato\",\"task\":\"Install hunt-ato\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review hunt-ato trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add elementalsouls-hunt-ato","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"hunt-ato\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session fixation, (6) JWT manipulation (forge token to another identity; crypto details → hunt-jwt-crypto), (7) password change without step-up (chain with login timing/length oracle), (8) social-recovery / security-question brute-force, (9) SSO subdomain takeover at OAuth redirect_uri. Chains: cookie theft + password oracle + no step-up = persistent ATO; lax redirect_uri = auth-code theft; dangling-CNAME takeover at redirect_uri = ATO. Validate: demonstrate real takeover of test account B from attacker A's session; OOB/Collaborator confirm blind token-leak steps. Use when hunting ATO chains, testing password reset / email change / MFA / OAuth / session / JWT, or chaining primitives t After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-ato\",\"task\":\"Install hunt-ato\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"hunt-ato\" as a Claude Code skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session fixation, (6) JWT manipulation (forge token to another identity; crypto details → hunt-jwt-crypto), (7) password change without step-up (chain with login timing/length oracle), (8) social-recovery / security-question brute-force, (9) SSO subdomain takeover at OAuth redirect_uri. Chains: cookie theft + password oracle + no step-up = persistent ATO; lax redirect_uri = auth-code theft; dangling-CNAME takeover at redirect_uri = ATO. Validate: demonstrate real takeover of test account B from attacker A's session; OOB/Collaborator confirm blind token-leak steps. Use when hunting ATO chains, testing password reset / email change / MFA / OAuth / session / JWT, or chaining primitives t After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-ato\",\"task\":\"Install hunt-ato\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"hunt-ato\" from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session fixation, (6) JWT manipulation (forge token to another identity; crypto details → hunt-jwt-crypto), (7) password change without step-up (chain with login timing/length oracle), (8) social-recovery / security-question brute-force, (9) SSO subdomain takeover at OAuth redirect_uri. Chains: cookie theft + password oracle + no step-up = persistent ATO; lax redirect_uri = auth-code theft; dangling-CNAME takeover at redirect_uri = ATO. Validate: demonstrate real takeover of test account B from attacker A's session; OOB/Collaborator confirm blind token-leak steps. Use when hunting ATO chains, testing password reset / email change / MFA / OAuth / session / JWT, or chaining primitives t After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-ato\",\"task\":\"Install hunt-ato\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"elementalsouls-hunt-ato","name":"hunt-ato","description":"Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session fixation, (6) JWT manipulation (forge token to another identity; crypto details → hunt-jwt-crypto), (7) password change without step-up (chain with login timing/length oracle), (8) social-recovery / security-question brute-force, (9) SSO subdomain takeover at OAuth redirect_uri. Chains: cookie theft + password oracle + no step-up = persistent ATO; lax redirect_uri = auth-code theft; dangling-CNAME takeover at redirect_uri = ATO. Validate: demonstrate real takeover of test account B from attacker A's session; OOB/Collaborator confirm blind token-leak steps. Use when hunting ATO chains, testing password reset / email change / MFA / OAuth / session / JWT, or chaining primitives t","category":"security","url":"https://www.openagentskill.com/skills/elementalsouls-hunt-ato","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato","github_repo":"elementalsouls/Claude-BugHunter"},"suited_tasks":["Testing and QA workflows","Claude Code teams","teams that value GitHub adoption signals","Run test suites","Capture failures","Report what changed after a fix","Inspect source files","Explain architecture"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add elementalsouls-hunt-ato"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"hunt-ato\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session fixation, (6) JWT manipulation (forge token to another identity; crypto details → hunt-jwt-crypto), (7) password change without step-up (chain with login timing/length oracle), (8) social-recovery / security-question brute-force, (9) SSO subdomain takeover at OAuth redirect_uri. Chains: cookie theft + password oracle + no step-up = persistent ATO; lax redirect_uri = auth-code theft; dangling-CNAME takeover at redirect_uri = ATO. Validate: demonstrate real takeover of test account B from attacker A's session; OOB/Collaborator confirm blind token-leak steps. Use when hunting ATO chains, testing password reset / email change / MFA / OAuth / session / JWT, or chaining primitives t After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-ato\",\"task\":\"Install hunt-ato\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"hunt-ato\" as a Claude Code skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session fixation, (6) JWT manipulation (forge token to another identity; crypto details → hunt-jwt-crypto), (7) password change without step-up (chain with login timing/length oracle), (8) social-recovery / security-question brute-force, (9) SSO subdomain takeover at OAuth redirect_uri. Chains: cookie theft + password oracle + no step-up = persistent ATO; lax redirect_uri = auth-code theft; dangling-CNAME takeover at redirect_uri = ATO. Validate: demonstrate real takeover of test account B from attacker A's session; OOB/Collaborator confirm blind token-leak steps. Use when hunting ATO chains, testing password reset / email change / MFA / OAuth / session / JWT, or chaining primitives t After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-ato\",\"task\":\"Install hunt-ato\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"hunt-ato\" from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session fixation, (6) JWT manipulation (forge token to another identity; crypto details → hunt-jwt-crypto), (7) password change without step-up (chain with login timing/length oracle), (8) social-recovery / security-question brute-force, (9) SSO subdomain takeover at OAuth redirect_uri. Chains: cookie theft + password oracle + no step-up = persistent ATO; lax redirect_uri = auth-code theft; dangling-CNAME takeover at redirect_uri = ATO. Validate: demonstrate real takeover of test account B from attacker A's session; OOB/Collaborator confirm blind token-leak steps. Use when hunting ATO chains, testing password reset / email change / MFA / OAuth / session / JWT, or chaining primitives t After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-ato\",\"task\":\"Install hunt-ato\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-ato/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/elementalsouls-hunt-ato"},"trust":{"score":72,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 637 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["security","agent-skill"],"known_risks":["No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":82,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Financial research output is not financial advice; require human review before any live investment decision","No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers.","Some paths (e.g., JWT manipulation) reference external skills (hunt-jwt-crypto) without linking them, which may require additional context.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":83,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Testing and QA","maintenance":"3d since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","No explicit setup or environment preparation section, though the skill is self-contained enough for experienced testers.","No OpenAgentSkill engagement data yet","High-risk permission hints: Secrets or environment access","Financial research output is not financial advice; require human review before any live investment decision","Some paths (e.g., JWT manipulation) reference external skills (hunt-jwt-crypto) without linking them, which may require additional context.","Financial research output is not financial advice; require human review before any live investment decision."],"agent_contract":{"task_input":"Use hunt-cache-poison","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 72/100 Strong shortlist","Audit: 82/100 Needs review","Safety: 58/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"elementalsouls-hunt-ato (hunt-ato)","install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-ato","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"elementalsouls-hunt-ato","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/elementalsouls-hunt-ato","api":"https://www.openagentskill.com/api/agent/skills/elementalsouls-hunt-ato","audit":"https://www.openagentskill.com/skills/elementalsouls-hunt-ato/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=elementalsouls-hunt-ato&task=Use%20hunt-cache-poison&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-ato/install","manifest":"https://www.openagentskill.com/api/registry/manifest/elementalsouls-hunt-ato"}},"use_cases":[{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/elementalsouls-hunt-ato","api":"https://www.openagentskill.com/api/agent/skills/elementalsouls-hunt-ato","install_api":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-ato/install","audit":"https://www.openagentskill.com/skills/elementalsouls-hunt-ato/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=elementalsouls-hunt-ato&task=Use%20hunt-cache-poison&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/elementalsouls-hunt-ato?metric=audit","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-ato"}},"new_contender":{"rank":12,"match_score":30,"raw_match_score":94.2,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"elementalsouls-hunt-auth-bypass","name":"hunt-auth-bypass","description":"Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024), partner-portal cross-IdP assertion reuse (Slack), WordPress XMLRPC bypassing SSO (Uber), JWT alg-confusion HS256/RS256 (Jitsi), JWT signature-validation skip (Linktree, Newspack), and token-audience confusion (Argo CD CVE-2023-22482). For standalone JWT signature/crypto forging (alg:none, key confusion, kid/jku) see hunt-jwt-crypto; this skill covers JWT only inside SSO/SAML/token-trust bypass chains. SAML assertion-layer attacks (XSW, comment injection, signature stripping, XXE-in-assertion) are owned by hunt-saml; this skill owns the broader cross-protocol auth-bypass taxonomy. Use when hunting auth bypass — see the Legacy-Protocol Matrix for branded-UI vs legacy-endpoint patterns","category":"security","github_stars":4098,"created_at":"2026-09-02T16:31:40.151733+00:00","updated_at":"2026-09-02T08:49:05+00:00","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass","github_repo":"elementalsouls/Claude-BugHunter","source_version":{"version":"1.0.0","commit_sha":"0efc24c3510d55bfef117d5594c0766df14f887b","content_hash":"7d8c2a013969817ceb337ecdb6afd04564727cfb0d9f2c2c86d5141020638e14","ref":"main","path":"skills/hunt-auth-bypass/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: hunt","Useful GitHub adoption: 4,098 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"document-processing","title":"Document processing"},{"slug":"github-automation","title":"GitHub automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":4098,"starsLabel":"4.1K","forks":637,"license":"MIT","qualityScore":83,"trustScore":72,"auditScore":82},"maintenance":{"status":"fresh","label":"3d since push","daysSincePush":3,"lastPushedAt":"2026-09-02T08:49:05+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Financial research output is not financial advice; require human review before any live investment decision","The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill.","The skill references other skills (hunt-jwt-crypto, hunt-saml) that are not included in this submission; users may need to obtain those separately for full coverage.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"coverageTags":["Coding","GitHub automation","security","agent-skill"]},"quality":{"score":83,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"4.1K","tone":"positive"},{"label":"Freshness","value":"3d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill."]},"trust":{"version":"trust-score-v4","score":72,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.1K stars, 637 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":74,"weight":0.07,"status":"info","detail":"secrets or environment access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.1K stars, 637 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"secrets or environment access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 637 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push","Financial domain: human review is required before use in a live investment workflow."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["security","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":64,"base_score":72,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["64/100 Trust Score v5","72/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.1K stars, 637 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":74,"weight":0.07,"status":"info","detail":"secrets or environment access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.1K stars, 637 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"secrets or environment access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 637 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push","Financial domain: human review is required before use in a live investment workflow.","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["security","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass","trust_score":64,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["security","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":72,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":82,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Financial research output is not financial advice; require human review before any live investment decision","The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill.","The skill references other skills (hunt-jwt-crypto, hunt-saml) that are not included in this submission; users may need to obtain those separately for full coverage.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"safety":{"score":58,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["High-risk permission hints: Secrets or environment access","58/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"secrets","label":"Secrets or environment access","reason":"Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.","severity":"high"}],"policy_warnings":["High-risk permission hints: Secrets or environment access","Financial research output is not financial advice; require human review before any live investment decision"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["High-risk permission hints: Secrets or environment access","58/100 agent safety score"]},"decision":{"readiness_score":94,"readiness_label":"Production-ready","headline":"Primary pick for Research agents","role":"Primary pick","best_for":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill.","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass","value":"Install the \"hunt-auth-bypass\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024), partner-portal cross-IdP assertion reuse (Slack), WordPress XMLRPC bypassing SSO (Uber), JWT alg-confusion HS256/RS256 (Jitsi), JWT signature-validation skip (Linktree, Newspack), and token-audience confusion (Argo CD CVE-2023-22482). For standalone JWT signature/crypto forging (alg:none, key confusion, kid/jku) see hunt-jwt-crypto; this skill covers JWT only inside SSO/SAML/token-trust bypass chains. SAML assertion-layer attacks (XSW, comment injection, signature stripping, XXE-in-assertion) are owned by hunt-saml; this skill owns the broader cross-protocol auth-bypass taxonomy. Use when hunting auth bypass — see the Legacy-Protocol Matrix for branded-UI vs legacy-endpoint patterns After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-auth-bypass\",\"task\":\"Install hunt-auth-bypass\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review hunt-auth-bypass trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add elementalsouls-hunt-auth-bypass","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"hunt-auth-bypass\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024), partner-portal cross-IdP assertion reuse (Slack), WordPress XMLRPC bypassing SSO (Uber), JWT alg-confusion HS256/RS256 (Jitsi), JWT signature-validation skip (Linktree, Newspack), and token-audience confusion (Argo CD CVE-2023-22482). For standalone JWT signature/crypto forging (alg:none, key confusion, kid/jku) see hunt-jwt-crypto; this skill covers JWT only inside SSO/SAML/token-trust bypass chains. SAML assertion-layer attacks (XSW, comment injection, signature stripping, XXE-in-assertion) are owned by hunt-saml; this skill owns the broader cross-protocol auth-bypass taxonomy. Use when hunting auth bypass — see the Legacy-Protocol Matrix for branded-UI vs legacy-endpoint patterns After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-auth-bypass\",\"task\":\"Install hunt-auth-bypass\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"hunt-auth-bypass\" as a Claude Code skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024), partner-portal cross-IdP assertion reuse (Slack), WordPress XMLRPC bypassing SSO (Uber), JWT alg-confusion HS256/RS256 (Jitsi), JWT signature-validation skip (Linktree, Newspack), and token-audience confusion (Argo CD CVE-2023-22482). For standalone JWT signature/crypto forging (alg:none, key confusion, kid/jku) see hunt-jwt-crypto; this skill covers JWT only inside SSO/SAML/token-trust bypass chains. SAML assertion-layer attacks (XSW, comment injection, signature stripping, XXE-in-assertion) are owned by hunt-saml; this skill owns the broader cross-protocol auth-bypass taxonomy. Use when hunting auth bypass — see the Legacy-Protocol Matrix for branded-UI vs legacy-endpoint patterns After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-auth-bypass\",\"task\":\"Install hunt-auth-bypass\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"hunt-auth-bypass\" from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024), partner-portal cross-IdP assertion reuse (Slack), WordPress XMLRPC bypassing SSO (Uber), JWT alg-confusion HS256/RS256 (Jitsi), JWT signature-validation skip (Linktree, Newspack), and token-audience confusion (Argo CD CVE-2023-22482). For standalone JWT signature/crypto forging (alg:none, key confusion, kid/jku) see hunt-jwt-crypto; this skill covers JWT only inside SSO/SAML/token-trust bypass chains. SAML assertion-layer attacks (XSW, comment injection, signature stripping, XXE-in-assertion) are owned by hunt-saml; this skill owns the broader cross-protocol auth-bypass taxonomy. Use when hunting auth bypass — see the Legacy-Protocol Matrix for branded-UI vs legacy-endpoint patterns After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-auth-bypass\",\"task\":\"Install hunt-auth-bypass\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"elementalsouls-hunt-auth-bypass","name":"hunt-auth-bypass","description":"Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024), partner-portal cross-IdP assertion reuse (Slack), WordPress XMLRPC bypassing SSO (Uber), JWT alg-confusion HS256/RS256 (Jitsi), JWT signature-validation skip (Linktree, Newspack), and token-audience confusion (Argo CD CVE-2023-22482). For standalone JWT signature/crypto forging (alg:none, key confusion, kid/jku) see hunt-jwt-crypto; this skill covers JWT only inside SSO/SAML/token-trust bypass chains. SAML assertion-layer attacks (XSW, comment injection, signature stripping, XXE-in-assertion) are owned by hunt-saml; this skill owns the broader cross-protocol auth-bypass taxonomy. Use when hunting auth bypass — see the Legacy-Protocol Matrix for branded-UI vs legacy-endpoint patterns","category":"security","url":"https://www.openagentskill.com/skills/elementalsouls-hunt-auth-bypass","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass","github_repo":"elementalsouls/Claude-BugHunter"},"suited_tasks":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Read uploaded files","Extract structured fields"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add elementalsouls-hunt-auth-bypass"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"hunt-auth-bypass\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024), partner-portal cross-IdP assertion reuse (Slack), WordPress XMLRPC bypassing SSO (Uber), JWT alg-confusion HS256/RS256 (Jitsi), JWT signature-validation skip (Linktree, Newspack), and token-audience confusion (Argo CD CVE-2023-22482). For standalone JWT signature/crypto forging (alg:none, key confusion, kid/jku) see hunt-jwt-crypto; this skill covers JWT only inside SSO/SAML/token-trust bypass chains. SAML assertion-layer attacks (XSW, comment injection, signature stripping, XXE-in-assertion) are owned by hunt-saml; this skill owns the broader cross-protocol auth-bypass taxonomy. Use when hunting auth bypass — see the Legacy-Protocol Matrix for branded-UI vs legacy-endpoint patterns After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-auth-bypass\",\"task\":\"Install hunt-auth-bypass\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"hunt-auth-bypass\" as a Claude Code skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024), partner-portal cross-IdP assertion reuse (Slack), WordPress XMLRPC bypassing SSO (Uber), JWT alg-confusion HS256/RS256 (Jitsi), JWT signature-validation skip (Linktree, Newspack), and token-audience confusion (Argo CD CVE-2023-22482). For standalone JWT signature/crypto forging (alg:none, key confusion, kid/jku) see hunt-jwt-crypto; this skill covers JWT only inside SSO/SAML/token-trust bypass chains. SAML assertion-layer attacks (XSW, comment injection, signature stripping, XXE-in-assertion) are owned by hunt-saml; this skill owns the broader cross-protocol auth-bypass taxonomy. Use when hunting auth bypass — see the Legacy-Protocol Matrix for branded-UI vs legacy-endpoint patterns After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-auth-bypass\",\"task\":\"Install hunt-auth-bypass\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"hunt-auth-bypass\" from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024), partner-portal cross-IdP assertion reuse (Slack), WordPress XMLRPC bypassing SSO (Uber), JWT alg-confusion HS256/RS256 (Jitsi), JWT signature-validation skip (Linktree, Newspack), and token-audience confusion (Argo CD CVE-2023-22482). For standalone JWT signature/crypto forging (alg:none, key confusion, kid/jku) see hunt-jwt-crypto; this skill covers JWT only inside SSO/SAML/token-trust bypass chains. SAML assertion-layer attacks (XSW, comment injection, signature stripping, XXE-in-assertion) are owned by hunt-saml; this skill owns the broader cross-protocol auth-bypass taxonomy. Use when hunting auth bypass — see the Legacy-Protocol Matrix for branded-UI vs legacy-endpoint patterns After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-auth-bypass\",\"task\":\"Install hunt-auth-bypass\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-auth-bypass/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/elementalsouls-hunt-auth-bypass"},"trust":{"score":72,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 637 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["security","agent-skill"],"known_risks":["The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":82,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Financial research output is not financial advice; require human review before any live investment decision","The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill.","The skill references other skills (hunt-jwt-crypto, hunt-saml) that are not included in this submission; users may need to obtain those separately for full coverage.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":83,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3d since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The SKILL.md excerpt is truncated in the review, but the provided content is sufficient to assess the skill.","No OpenAgentSkill engagement data yet","High-risk permission hints: Secrets or environment access","Financial research output is not financial advice; require human review before any live investment decision","The skill references other skills (hunt-jwt-crypto, hunt-saml) that are not included in this submission; users may need to obtain those separately for full coverage.","Financial research output is not financial advice; require human review before any live investment decision."],"agent_contract":{"task_input":"Use hunt-cache-poison","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 72/100 Strong shortlist","Audit: 82/100 Needs review","Safety: 58/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"elementalsouls-hunt-auth-bypass (hunt-auth-bypass)","install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-auth-bypass","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"elementalsouls-hunt-auth-bypass","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/elementalsouls-hunt-auth-bypass","api":"https://www.openagentskill.com/api/agent/skills/elementalsouls-hunt-auth-bypass","audit":"https://www.openagentskill.com/skills/elementalsouls-hunt-auth-bypass/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=elementalsouls-hunt-auth-bypass&task=Use%20hunt-cache-poison&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-auth-bypass/install","manifest":"https://www.openagentskill.com/api/registry/manifest/elementalsouls-hunt-auth-bypass"}},"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/elementalsouls-hunt-auth-bypass","api":"https://www.openagentskill.com/api/agent/skills/elementalsouls-hunt-auth-bypass","install_api":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-auth-bypass/install","audit":"https://www.openagentskill.com/skills/elementalsouls-hunt-auth-bypass/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=elementalsouls-hunt-auth-bypass&task=Use%20hunt-cache-poison&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/elementalsouls-hunt-auth-bypass?metric=audit","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-auth-bypass"}},"no_skill_option":{"recommended":true,"label":"Build without a third-party skill","reason":"Use a native agent workflow when the third-party permission or maintenance surface is not acceptable.","action":"Use the agent’s built-in tools for one narrow run, then reconsider a skill only if the workflow repeats."}},"selected":{"rank":4,"match_score":30,"raw_match_score":103,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"zilliztech-gptcache","name":"GPTCache","description":"Semantic cache for LLMs. Fully integrated with LangChain and llama_index. ","category":"rag-knowledge","github_stars":8067,"created_at":"2026-06-05T06:01:49.808031+00:00","updated_at":"2025-07-11T09:04:36+00:00","repository":"https://github.com/zilliztech/GPTCache","github_repo":"zilliztech/GPTCache","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: cache","Useful GitHub adoption: 8,067 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"research-agents","title":"Research agents"},{"slug":"customer-support","title":"Customer support"}]},"applicableAgents":["OpenAI Agents","LangChain","CLI","Codex","Claude Code"],"install":{"ready":true,"command":"npx skills add zilliztech/GPTCache","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":8067,"starsLabel":"8.1K","forks":583,"license":"MIT","qualityScore":74,"trustScore":79,"auditScore":74},"maintenance":{"status":"stale","label":"1y since push","daysSincePush":421,"lastPushedAt":"2025-07-11T09:04:36+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"coverageTags":["Research","RAG and knowledge","rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"]},"quality":{"score":74,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"8.1K","tone":"positive"},{"label":"Freshness","value":"1y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":79,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"8.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"8.1K stars, 583 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add zilliztech/GPTCache"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/zilliztech/GPTCache"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"8.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"8.1K stars, 583 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add zilliztech/GPTCache"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/zilliztech/GPTCache"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"OpenAgentSkill usage","detail":"6 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"8.1K GitHub stars","repoActivity":"8.1K stars, 583 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/zilliztech/GPTCache","install":"npx skills add zilliztech/GPTCache","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add zilliztech/GPTCache","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","1y since push"]},"agentCompatibility":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":71,"base_score":79,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["71/100 Trust Score v5","79/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"8.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"8.1K stars, 583 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add zilliztech/GPTCache"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/zilliztech/GPTCache"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"8.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"8.1K stars, 583 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add zilliztech/GPTCache"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/zilliztech/GPTCache"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"OpenAgentSkill usage","detail":"6 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"8.1K GitHub stars","repoActivity":"8.1K stars, 583 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/zilliztech/GPTCache","install":"npx skills add zilliztech/GPTCache","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add zilliztech/GPTCache","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","1y since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add zilliztech/GPTCache","trust_score":71,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":79,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"safety":{"score":62,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","62/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","62/100 agent safety score"]},"decision":{"readiness_score":79,"readiness_label":"Strong shortlist","headline":"Companion skill for RAG and knowledge","role":"Companion skill","best_for":["RAG and knowledge workflows","OpenAI Agents teams","teams that value GitHub adoption signals"],"risks":["Repository looks stale"],"next_steps":["Install it in a sandbox agent and run one RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add zilliztech/GPTCache","value":"Install the \"GPTCache\" agent skill from https://github.com/zilliztech/GPTCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review GPTCache trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add zilliztech-gptcache","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"GPTCache\" agent skill from https://github.com/zilliztech/GPTCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"GPTCache\" as a Claude Code skill from https://github.com/zilliztech/GPTCache. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"GPTCache\" from https://github.com/zilliztech/GPTCache into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"zilliztech-gptcache","name":"GPTCache","description":"Semantic cache for LLMs. Fully integrated with LangChain and llama_index. ","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/zilliztech-gptcache","repository":"https://github.com/zilliztech/GPTCache","github_repo":"zilliztech/GPTCache"},"suited_tasks":["RAG and knowledge workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","LangChain"],"install":{"command":"npx skills add zilliztech/GPTCache","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add zilliztech-gptcache"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"GPTCache\" agent skill from https://github.com/zilliztech/GPTCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"GPTCache\" as a Claude Code skill from https://github.com/zilliztech/GPTCache. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"GPTCache\" from https://github.com/zilliztech/GPTCache into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zilliztech-gptcache"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"8.1K GitHub stars","repoActivity":"8.1K stars, 583 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/zilliztech/GPTCache","install":"npx skills add zilliztech/GPTCache","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["rag-knowledge","semantic-search","retrieval","knowledge","aigc","autogpt"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":74,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"agent_contract":{"task_input":"Use hunt-cache-poison","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 74/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zilliztech-gptcache (GPTCache)","install_command":"npx skills add zilliztech/GPTCache","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"zilliztech-gptcache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/zilliztech-gptcache","api":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache","audit":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zilliztech-gptcache"}},"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"customer-support","title":"Customer support","url":"https://www.openagentskill.com/use-cases/customer-support"}],"urls":{"web":"https://www.openagentskill.com/skills/zilliztech-gptcache","api":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache","install_api":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install","audit":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/zilliztech-gptcache?metric=audit","repository":"https://github.com/zilliztech/GPTCache"}},"alternatives":[{"rank":1,"match_score":54,"raw_match_score":222.2,"semantic_relevance":54,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"elementalsouls-hunt-cache-poison","name":"hunt-cache-poison","description":"Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session-token cache deception, Akamai hop-by-hop smuggling → server-side edge poisoning, and Kettle's 2024 path-normalization WCD against Cloudflare/Fastly/GCP. Host/X-Forwarded-Host injection that reaches app logic (reset-link poisoning, routing SSRF, OAuth issuer) is owned by hunt-host-header; this skill owns the case where the poisoned response is CACHED and served to other users. Use when hunting cache poisoning, Web Cache Deception, CDN-fronted apps.","category":"security","github_stars":4086,"created_at":"2026-09-02T15:10:33.939853+00:00","updated_at":"2026-09-02T08:49:05+00:00","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison","github_repo":"elementalsouls/Claude-BugHunter","source_version":{"version":"1.0.0","commit_sha":"0efc24c3510d55bfef117d5594c0766df14f887b","content_hash":"a64dea2f7b69bcfbc6d03c21ca8fa0ddf78bc481ecc6531c9f6064737879f25d","ref":"main","path":"skills/hunt-cache-poison/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: hunt, cache, poison","Useful GitHub adoption: 4,086 stars","Install handoff is available","Repository freshness signal is available","Registry match score 54"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"research-agents","title":"Research agents"},{"slug":"github-automation","title":"GitHub automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":4086,"starsLabel":"4.1K","forks":634,"license":"MIT","qualityScore":83,"trustScore":68,"auditScore":81},"maintenance":{"status":"fresh","label":"3d since push","daysSincePush":3,"lastPushedAt":"2026-09-02T08:49:05+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Permission surface may require sandboxing","SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Description mentions 10 public bug bounty reports but report_count is 8 - inconsistency.","No explicit statement about only testing on authorized targets, though implied by bug bounty context.","Quality score needs review"]},"coverageTags":["Coding","GitHub automation","security","agent-skill"]},"quality":{"score":83,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"4.1K","tone":"positive"},{"label":"Freshness","value":"3d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete."]},"trust":{"version":"trust-score-v4","score":68,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection.","recommendedAction":"Inspect the repository, license, and recent activity before connecting it to agent workflows.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.1K stars, 634 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":64,"weight":0.12,"status":"info","detail":"credential or environment access, network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":60,"weight":0.07,"status":"warn","detail":"secrets or environment access, network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.1K stars, 634 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"credential or environment access, network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"warn","label":"Permission surface","detail":"secrets or environment access, network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Quality score needs review","Permission surface needs review: secrets or environment access, network or browser access","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Permission surface: secrets or environment access, network or browser access"],"evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 634 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Quality score needs review","Permission surface needs review: secrets or environment access, network or browser access","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Permission surface: secrets or environment access, network or browser access"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["security","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Quality score needs review","Permission surface needs review: secrets or environment access, network or browser access","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Permission surface: secrets or environment access, network or browser access"]},"trust_v5":{"version":"trust-score-v5","score":60,"base_score":68,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["60/100 Trust Score v5","68/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.1K stars, 634 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":64,"weight":0.12,"status":"info","detail":"credential or environment access, network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":60,"weight":0.07,"status":"warn","detail":"secrets or environment access, network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.1K stars, 634 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"credential or environment access, network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"warn","label":"Permission surface","detail":"secrets or environment access, network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Quality score needs review","Permission surface needs review: secrets or environment access, network or browser access","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Permission surface: secrets or environment access, network or browser access","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 634 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Quality score needs review","Permission surface needs review: secrets or environment access, network or browser access","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Permission surface: secrets or environment access, network or browser access"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["security","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","trust_score":60,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["security","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Quality score needs review","Permission surface needs review: secrets or environment access, network or browser access","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Permission surface: secrets or environment access, network or browser access"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":68,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Permission surface may require sandboxing","SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Description mentions 10 public bug bounty reports but report_count is 8 - inconsistency.","No explicit statement about only testing on authorized targets, though implied by bug bounty context.","Quality score needs review"]},"safety":{"score":57,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["High-risk permission hints: Secrets or environment access","57/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"secrets","label":"Secrets or environment access","reason":"Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.","severity":"high"}],"policy_warnings":["High-risk permission hints: Secrets or environment access","Permission surface may require sandboxing"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["High-risk permission hints: Secrets or environment access","57/100 agent safety score"]},"decision":{"readiness_score":94,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","best_for":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","value":"Install the \"hunt-cache-poison\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session-token cache deception, Akamai hop-by-hop smuggling → server-side edge poisoning, and Kettle's 2024 path-normalization WCD against Cloudflare/Fastly/GCP. Host/X-Forwarded-Host injection that reaches app logic (reset-link poisoning, routing SSRF, OAuth issuer) is owned by hunt-host-header; this skill owns the case where the poisoned response is CACHED and served to other users. Use when hunting cache poisoning, Web Cache Deception, CDN-fronted apps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cache-poison\",\"task\":\"Install hunt-cache-poison\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review hunt-cache-poison trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add elementalsouls-hunt-cache-poison","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"hunt-cache-poison\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session-token cache deception, Akamai hop-by-hop smuggling → server-side edge poisoning, and Kettle's 2024 path-normalization WCD against Cloudflare/Fastly/GCP. Host/X-Forwarded-Host injection that reaches app logic (reset-link poisoning, routing SSRF, OAuth issuer) is owned by hunt-host-header; this skill owns the case where the poisoned response is CACHED and served to other users. Use when hunting cache poisoning, Web Cache Deception, CDN-fronted apps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cache-poison\",\"task\":\"Install hunt-cache-poison\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"hunt-cache-poison\" as a Claude Code skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session-token cache deception, Akamai hop-by-hop smuggling → server-side edge poisoning, and Kettle's 2024 path-normalization WCD against Cloudflare/Fastly/GCP. Host/X-Forwarded-Host injection that reaches app logic (reset-link poisoning, routing SSRF, OAuth issuer) is owned by hunt-host-header; this skill owns the case where the poisoned response is CACHED and served to other users. Use when hunting cache poisoning, Web Cache Deception, CDN-fronted apps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cache-poison\",\"task\":\"Install hunt-cache-poison\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"hunt-cache-poison\" from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session-token cache deception, Akamai hop-by-hop smuggling → server-side edge poisoning, and Kettle's 2024 path-normalization WCD against Cloudflare/Fastly/GCP. Host/X-Forwarded-Host injection that reaches app logic (reset-link poisoning, routing SSRF, OAuth issuer) is owned by hunt-host-header; this skill owns the case where the poisoned response is CACHED and served to other users. Use when hunting cache poisoning, Web Cache Deception, CDN-fronted apps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cache-poison\",\"task\":\"Install hunt-cache-poison\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"elementalsouls-hunt-cache-poison","name":"hunt-cache-poison","description":"Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session-token cache deception, Akamai hop-by-hop smuggling → server-side edge poisoning, and Kettle's 2024 path-normalization WCD against Cloudflare/Fastly/GCP. Host/X-Forwarded-Host injection that reaches app logic (reset-link poisoning, routing SSRF, OAuth issuer) is owned by hunt-host-header; this skill owns the case where the poisoned response is CACHED and served to other users. Use when hunting cache poisoning, Web Cache Deception, CDN-fronted apps.","category":"security","url":"https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison","github_repo":"elementalsouls/Claude-BugHunter"},"suited_tasks":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Search sources","Extract claims"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add elementalsouls-hunt-cache-poison"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"hunt-cache-poison\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session-token cache deception, Akamai hop-by-hop smuggling → server-side edge poisoning, and Kettle's 2024 path-normalization WCD against Cloudflare/Fastly/GCP. Host/X-Forwarded-Host injection that reaches app logic (reset-link poisoning, routing SSRF, OAuth issuer) is owned by hunt-host-header; this skill owns the case where the poisoned response is CACHED and served to other users. Use when hunting cache poisoning, Web Cache Deception, CDN-fronted apps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cache-poison\",\"task\":\"Install hunt-cache-poison\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"hunt-cache-poison\" as a Claude Code skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session-token cache deception, Akamai hop-by-hop smuggling → server-side edge poisoning, and Kettle's 2024 path-normalization WCD against Cloudflare/Fastly/GCP. Host/X-Forwarded-Host injection that reaches app logic (reset-link poisoning, routing SSRF, OAuth issuer) is owned by hunt-host-header; this skill owns the case where the poisoned response is CACHED and served to other users. Use when hunting cache poisoning, Web Cache Deception, CDN-fronted apps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cache-poison\",\"task\":\"Install hunt-cache-poison\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"hunt-cache-poison\" from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session-token cache deception, Akamai hop-by-hop smuggling → server-side edge poisoning, and Kettle's 2024 path-normalization WCD against Cloudflare/Fastly/GCP. Host/X-Forwarded-Host injection that reaches app logic (reset-link poisoning, routing SSRF, OAuth issuer) is owned by hunt-host-header; this skill owns the case where the poisoned response is CACHED and served to other users. Use when hunting cache poisoning, Web Cache Deception, CDN-fronted apps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cache-poison\",\"task\":\"Install hunt-cache-poison\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-cache-poison/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/elementalsouls-hunt-cache-poison"},"trust":{"score":68,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 634 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["security","agent-skill"],"known_risks":["SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Quality score needs review","Permission surface needs review: secrets or environment access, network or browser access","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Permission surface: secrets or environment access, network or browser access"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Permission surface may require sandboxing","SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Description mentions 10 public bug bounty reports but report_count is 8 - inconsistency.","No explicit statement about only testing on authorized targets, though implied by bug bounty context.","Quality score needs review","Permission surface needs review: secrets or environment access, network or browser access","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Permission surface: secrets or environment access, network or browser access"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":83,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3d since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","No OpenAgentSkill engagement data yet","High-risk permission hints: Secrets or environment access","Permission surface may require sandboxing","Description mentions 10 public bug bounty reports but report_count is 8 - inconsistency.","No explicit statement about only testing on authorized targets, though implied by bug bounty context."],"agent_contract":{"task_input":"Use hunt-cache-poison","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 68/100 Manual review","Audit: 81/100 Needs review","Safety: 57/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"elementalsouls-hunt-cache-poison (hunt-cache-poison)","install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"elementalsouls-hunt-cache-poison","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison","api":"https://www.openagentskill.com/api/agent/skills/elementalsouls-hunt-cache-poison","audit":"https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=elementalsouls-hunt-cache-poison&task=Use%20hunt-cache-poison&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-cache-poison/install","manifest":"https://www.openagentskill.com/api/registry/manifest/elementalsouls-hunt-cache-poison"}},"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison","api":"https://www.openagentskill.com/api/agent/skills/elementalsouls-hunt-cache-poison","install_api":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-cache-poison/install","audit":"https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=elementalsouls-hunt-cache-poison&task=Use%20hunt-cache-poison&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/elementalsouls-hunt-cache-poison?metric=audit","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cache-poison"}},{"rank":2,"match_score":30,"raw_match_score":112.5,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"cnighswonger-claude-code-cache-fix","name":"Claude Code Cache Fix","description":"Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions","category":"coding-agents","github_stars":308,"created_at":"2026-06-20T20:11:23.490396+00:00","updated_at":"2026-06-20T16:09:20+00:00","repository":"https://github.com/cnighswonger/claude-code-cache-fix","github_repo":"cnighswonger/claude-code-cache-fix","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: cache","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","JavaScript"],"install":{"ready":true,"command":"npx skills add cnighswonger/claude-code-cache-fix","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":308,"starsLabel":"308","forks":22,"license":"Unknown","qualityScore":65,"trustScore":70,"auditScore":74},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":76,"lastPushedAt":"2026-06-20T16:09:20+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"coverageTags":["Coding","Coding agents","coding-agents","developer-tools","automation","anthropic","api-proxy","cache"]},"quality":{"score":65,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"308","tone":"neutral"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":70,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection.","recommendedAction":"Inspect the repository, license, and recent activity before connecting it to agent workflows.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"308 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"308 stars, 22 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"3mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":64,"weight":0.12,"status":"info","detail":"command execution surface, network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add cnighswonger/claude-code-cache-fix"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":62,"weight":0.07,"status":"info","detail":"shell or command execution, network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/cnighswonger/claude-code-cache-fix"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"308 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"308 stars, 22 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface, network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add cnighswonger/claude-code-cache-fix"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution, network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/cnighswonger/claude-code-cache-fix"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata","License clarity: Unknown"],"evidence":{"stars":"308 GitHub stars","repoActivity":"308 stars, 22 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/cnighswonger/claude-code-cache-fix","install":"npx skills add cnighswonger/claude-code-cache-fix","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add cnighswonger/claude-code-cache-fix","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","3mo since push"]},"agentCompatibility":["JavaScript","Developer Tools","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["coding-agents","developer-tools","automation","coding","anthropic","api-proxy"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"trust_v5":{"version":"trust-score-v5","score":62,"base_score":70,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["62/100 Trust Score v5","70/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"308 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"308 stars, 22 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"3mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":64,"weight":0.12,"status":"info","detail":"command execution surface, network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add cnighswonger/claude-code-cache-fix"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":62,"weight":0.07,"status":"info","detail":"shell or command execution, network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/cnighswonger/claude-code-cache-fix"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"308 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"308 stars, 22 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface, network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add cnighswonger/claude-code-cache-fix"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution, network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/cnighswonger/claude-code-cache-fix"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata","License clarity: Unknown","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"308 GitHub stars","repoActivity":"308 stars, 22 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/cnighswonger/claude-code-cache-fix","install":"npx skills add cnighswonger/claude-code-cache-fix","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add cnighswonger/claude-code-cache-fix","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","3mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["JavaScript","Developer Tools","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["coding-agents","developer-tools","automation","coding","anthropic","api-proxy"],"suited_agents":["JavaScript","Developer Tools","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add cnighswonger/claude-code-cache-fix","trust_score":62,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["coding-agents","developer-tools","automation","coding","anthropic","api-proxy"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata","License clarity: Unknown"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":70,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"safety":{"score":50,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","50/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["High-risk permission hints: Shell or command execution","50/100 agent safety score"]},"decision":{"readiness_score":64,"readiness_label":"Prototype first","headline":"Fallback candidate for Coding agents","role":"Fallback candidate","best_for":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add cnighswonger/claude-code-cache-fix","value":"Install the \"Claude Code Cache Fix\" agent skill from https://github.com/cnighswonger/claude-code-cache-fix. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cnighswonger-claude-code-cache-fix\",\"task\":\"Install Claude Code Cache Fix\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Claude Code Cache Fix trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add cnighswonger-claude-code-cache-fix","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Claude Code Cache Fix\" agent skill from https://github.com/cnighswonger/claude-code-cache-fix. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cnighswonger-claude-code-cache-fix\",\"task\":\"Install Claude Code Cache Fix\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Claude Code Cache Fix\" as a Claude Code skill from https://github.com/cnighswonger/claude-code-cache-fix. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cnighswonger-claude-code-cache-fix\",\"task\":\"Install Claude Code Cache Fix\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Claude Code Cache Fix\" from https://github.com/cnighswonger/claude-code-cache-fix into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cnighswonger-claude-code-cache-fix\",\"task\":\"Install Claude Code Cache Fix\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"cnighswonger-claude-code-cache-fix","name":"Claude Code Cache Fix","description":"Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions","category":"coding-agents","url":"https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix","repository":"https://github.com/cnighswonger/claude-code-cache-fix","github_repo":"cnighswonger/claude-code-cache-fix"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["JavaScript","Developer Tools","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add cnighswonger/claude-code-cache-fix","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add cnighswonger-claude-code-cache-fix"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Claude Code Cache Fix\" agent skill from https://github.com/cnighswonger/claude-code-cache-fix. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cnighswonger-claude-code-cache-fix\",\"task\":\"Install Claude Code Cache Fix\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Claude Code Cache Fix\" as a Claude Code skill from https://github.com/cnighswonger/claude-code-cache-fix. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cnighswonger-claude-code-cache-fix\",\"task\":\"Install Claude Code Cache Fix\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Claude Code Cache Fix\" from https://github.com/cnighswonger/claude-code-cache-fix into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"cnighswonger-claude-code-cache-fix\",\"task\":\"Install Claude Code Cache Fix\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/cnighswonger-claude-code-cache-fix/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/cnighswonger-claude-code-cache-fix"},"trust":{"score":70,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"308 GitHub stars","repoActivity":"308 stars, 22 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/cnighswonger/claude-code-cache-fix","install":"npx skills add cnighswonger/claude-code-cache-fix","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","developer-tools","automation","coding","anthropic","api-proxy"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":65,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use hunt-cache-poison","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 70/100 Manual review","Audit: 74/100 Needs review","Safety: 50/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"cnighswonger-claude-code-cache-fix (Claude Code Cache Fix)","install_command":"npx skills add cnighswonger/claude-code-cache-fix","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"cnighswonger-claude-code-cache-fix","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix","api":"https://www.openagentskill.com/api/agent/skills/cnighswonger-claude-code-cache-fix","audit":"https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=cnighswonger-claude-code-cache-fix&task=Use%20hunt-cache-poison&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/cnighswonger-claude-code-cache-fix/install","manifest":"https://www.openagentskill.com/api/registry/manifest/cnighswonger-claude-code-cache-fix"}},"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix","api":"https://www.openagentskill.com/api/agent/skills/cnighswonger-claude-code-cache-fix","install_api":"https://www.openagentskill.com/api/skills/cnighswonger-claude-code-cache-fix/install","audit":"https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=cnighswonger-claude-code-cache-fix&task=Use%20hunt-cache-poison&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/cnighswonger-claude-code-cache-fix?metric=audit","repository":"https://github.com/cnighswonger/claude-code-cache-fix"}},{"rank":3,"match_score":30,"raw_match_score":106.4,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"hackmanit-web-cache-vulnerability-scanner","name":"Web Cache Vulnerability Scanner","description":"Web Cache Vulnerability Scanner is a Go-based CLI tool for testing for web cache poisoning. It is developed by Hackmanit GmbH (http://hackmanit.de/).","category":"security","github_stars":1178,"created_at":"2026-06-06T05:01:05.872659+00:00","updated_at":"2026-01-21T10:18:50+00:00","repository":"https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner","github_repo":"Hackmanit/Web-Cache-Vulnerability-Scanner","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: cache","Useful GitHub adoption: 1,178 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Testing and QA","description":"I need my agent to test a web app, reproduce bugs, and verify fixes.","useCases":[{"slug":"security-compliance","title":"Security and compliance"},{"slug":"testing-qa","title":"Testing and QA"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Go"],"install":{"ready":true,"command":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1178,"starsLabel":"1.2K","forks":159,"license":"Apache-2.0","qualityScore":78,"trustScore":79,"auditScore":78},"maintenance":{"status":"stable","label":"8mo since push","daysSincePush":226,"lastPushedAt":"2026-01-21T10:18:50+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin","Needs review"]},"coverageTags":["Coding","Testing and QA","security","scanner","bugbounty","hacking","hacking-tool","penetration-testing"]},"quality":{"score":78,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"1.2K","tone":"positive"},{"label":"Freshness","value":"8mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":79,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"1.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.2K stars, 159 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"8mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":64,"weight":0.12,"status":"info","detail":"command execution surface, network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":62,"weight":0.07,"status":"info","detail":"shell or command execution, network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"1.2K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.2K stars, 159 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"8mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface, network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution, network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin"],"evidence":{"stars":"1.2K GitHub stars","repoActivity":"1.2K stars, 159 forks","lastPushed":"8mo since push","license":"Apache-2.0","repository":"https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner","install":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","8mo since push"]},"agentCompatibility":["Go","Security","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["security","scanner","bugbounty","hacking","hacking-tool","penetration-testing"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin"]},"trust_v5":{"version":"trust-score-v5","score":71,"base_score":79,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["71/100 Trust Score v5","79/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"1.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.2K stars, 159 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"8mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":64,"weight":0.12,"status":"info","detail":"command execution surface, network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":62,"weight":0.07,"status":"info","detail":"shell or command execution, network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"1.2K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.2K stars, 159 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"8mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface, network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution, network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Quality score needs review","Documentation summary is thin","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"1.2K GitHub stars","repoActivity":"1.2K stars, 159 forks","lastPushed":"8mo since push","license":"Apache-2.0","repository":"https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner","install":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","8mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Go","Security","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["security","scanner","bugbounty","hacking","hacking-tool","penetration-testing"],"suited_agents":["Go","Security","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","trust_score":71,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["security","scanner","bugbounty","hacking","hacking-tool","penetration-testing"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":79,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin"]},"safety":{"score":54,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","54/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["High-risk permission hints: Shell or command execution","54/100 agent safety score"]},"decision":{"readiness_score":80,"readiness_label":"Strong shortlist","headline":"Companion skill for Security and compliance","role":"Companion skill","best_for":["Security and compliance workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Security and compliance task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","value":"Install the \"Web Cache Vulnerability Scanner\" agent skill from https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Web Cache Vulnerability Scanner is a Go-based CLI tool for testing for web cache poisoning. It is developed by Hackmanit GmbH (http://hackmanit.de/). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"hackmanit-web-cache-vulnerability-scanner\",\"task\":\"Install Web Cache Vulnerability Scanner\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Web Cache Vulnerability Scanner trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add hackmanit-web-cache-vulnerability-scanner","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Web Cache Vulnerability Scanner\" agent skill from https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Web Cache Vulnerability Scanner is a Go-based CLI tool for testing for web cache poisoning. It is developed by Hackmanit GmbH (http://hackmanit.de/). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"hackmanit-web-cache-vulnerability-scanner\",\"task\":\"Install Web Cache Vulnerability Scanner\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Web Cache Vulnerability Scanner\" as a Claude Code skill from https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Web Cache Vulnerability Scanner is a Go-based CLI tool for testing for web cache poisoning. It is developed by Hackmanit GmbH (http://hackmanit.de/). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"hackmanit-web-cache-vulnerability-scanner\",\"task\":\"Install Web Cache Vulnerability Scanner\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Web Cache Vulnerability Scanner\" from https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Web Cache Vulnerability Scanner is a Go-based CLI tool for testing for web cache poisoning. It is developed by Hackmanit GmbH (http://hackmanit.de/). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"hackmanit-web-cache-vulnerability-scanner\",\"task\":\"Install Web Cache Vulnerability Scanner\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"hackmanit-web-cache-vulnerability-scanner","name":"Web Cache Vulnerability Scanner","description":"Web Cache Vulnerability Scanner is a Go-based CLI tool for testing for web cache poisoning. It is developed by Hackmanit GmbH (http://hackmanit.de/).","category":"security","url":"https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner","repository":"https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner","github_repo":"Hackmanit/Web-Cache-Vulnerability-Scanner"},"suited_tasks":["Security and compliance workflows","general agent builders","teams that value GitHub adoption signals","Inspect risky files","Prioritize findings","Explain remediation steps","Run test suites","Capture failures"],"suited_agents":["Go","Security","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add hackmanit-web-cache-vulnerability-scanner"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Web Cache Vulnerability Scanner\" agent skill from https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Web Cache Vulnerability Scanner is a Go-based CLI tool for testing for web cache poisoning. It is developed by Hackmanit GmbH (http://hackmanit.de/). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"hackmanit-web-cache-vulnerability-scanner\",\"task\":\"Install Web Cache Vulnerability Scanner\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Web Cache Vulnerability Scanner\" as a Claude Code skill from https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Web Cache Vulnerability Scanner is a Go-based CLI tool for testing for web cache poisoning. It is developed by Hackmanit GmbH (http://hackmanit.de/). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"hackmanit-web-cache-vulnerability-scanner\",\"task\":\"Install Web Cache Vulnerability Scanner\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Web Cache Vulnerability Scanner\" from https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Web Cache Vulnerability Scanner is a Go-based CLI tool for testing for web cache poisoning. It is developed by Hackmanit GmbH (http://hackmanit.de/). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"hackmanit-web-cache-vulnerability-scanner\",\"task\":\"Install Web Cache Vulnerability Scanner\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/hackmanit-web-cache-vulnerability-scanner/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/hackmanit-web-cache-vulnerability-scanner"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.2K GitHub stars","repoActivity":"1.2K stars, 159 forks","lastPushed":"8mo since push","license":"Apache-2.0","repository":"https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner","install":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["security","scanner","bugbounty","hacking","hacking-tool","penetration-testing"],"known_risks":["Quality score needs review","Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":78,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Testing and QA","maintenance":"8mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Quality score needs review","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use hunt-cache-poison","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 54/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"hackmanit-web-cache-vulnerability-scanner (Web Cache Vulnerability Scanner)","install_command":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"hackmanit-web-cache-vulnerability-scanner","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner","api":"https://www.openagentskill.com/api/agent/skills/hackmanit-web-cache-vulnerability-scanner","audit":"https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=hackmanit-web-cache-vulnerability-scanner&task=Use%20hunt-cache-poison&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/hackmanit-web-cache-vulnerability-scanner/install","manifest":"https://www.openagentskill.com/api/registry/manifest/hackmanit-web-cache-vulnerability-scanner"}},"use_cases":[{"slug":"security-compliance","title":"Security and compliance","url":"https://www.openagentskill.com/use-cases/security-compliance"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"urls":{"web":"https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner","api":"https://www.openagentskill.com/api/agent/skills/hackmanit-web-cache-vulnerability-scanner","install_api":"https://www.openagentskill.com/api/skills/hackmanit-web-cache-vulnerability-scanner/install","audit":"https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=hackmanit-web-cache-vulnerability-scanner&task=Use%20hunt-cache-poison&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/hackmanit-web-cache-vulnerability-scanner?metric=audit","repository":"https://github.com/Hackmanit/Web-Cache-Vulnerability-Scanner"}},{"rank":6,"match_score":30,"raw_match_score":97.8,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"ali-vilab-teacache","name":"TeaCache","description":"Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model","category":"media-automation","github_stars":1366,"created_at":"2026-06-16T10:05:01.231745+00:00","updated_at":"2025-06-08T14:29:09+00:00","repository":"https://github.com/ali-vilab/TeaCache","github_repo":"ali-vilab/TeaCache","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: cache","Useful GitHub adoption: 1,366 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Design and creative","description":"I need my agent to produce design assets, UI directions, presentations, or creative media workflows.","useCases":[{"slug":"design-creative","title":"Design and creative"},{"slug":"video-creation","title":"Video creation"},{"slug":"multimodal-media","title":"Multimodal media"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add ali-vilab/TeaCache","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1366,"starsLabel":"1.4K","forks":60,"license":"Apache-2.0","qualityScore":66,"trustScore":79,"auditScore":72},"maintenance":{"status":"stale","label":"1y since push","daysSincePush":453,"lastPushedAt":"2025-06-08T14:29:09+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"coverageTags":["Design","Design and creative","media-automation","video-generation","creative","media","cogvideox","diffusion-models"]},"quality":{"score":66,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"1.4K","tone":"positive"},{"label":"Freshness","value":"1y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":79,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"1.4K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.4K stars, 60 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add ali-vilab/TeaCache"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/ali-vilab/TeaCache"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"1.4K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.4K stars, 60 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add ali-vilab/TeaCache"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/ali-vilab/TeaCache"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"1.4K GitHub stars","repoActivity":"1.4K stars, 60 forks","lastPushed":"1y since push","license":"Apache-2.0","repository":"https://github.com/ali-vilab/TeaCache","install":"npx skills add ali-vilab/TeaCache","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add ali-vilab/TeaCache","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","1y since push"]},"agentCompatibility":["Python","Video Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["media-automation","video-generation","creative","media","design","cogvideox"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":71,"base_score":79,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["71/100 Trust Score v5","79/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"1.4K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.4K stars, 60 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add ali-vilab/TeaCache"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/ali-vilab/TeaCache"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"1.4K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.4K stars, 60 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add ali-vilab/TeaCache"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/ali-vilab/TeaCache"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"1.4K GitHub stars","repoActivity":"1.4K stars, 60 forks","lastPushed":"1y since push","license":"Apache-2.0","repository":"https://github.com/ali-vilab/TeaCache","install":"npx skills add ali-vilab/TeaCache","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add ali-vilab/TeaCache","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","1y since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","Video Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["media-automation","video-generation","creative","media","design","cogvideox"],"suited_agents":["Python","Video Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add ali-vilab/TeaCache","trust_score":71,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["media-automation","video-generation","creative","media","design","cogvideox"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":79,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":72,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"safety":{"score":60,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","60/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","60/100 agent safety score"]},"decision":{"readiness_score":68,"readiness_label":"Prototype first","headline":"Fallback candidate for Design and creative","role":"Fallback candidate","best_for":["Design and creative workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Design and creative task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add ali-vilab/TeaCache","value":"Install the \"TeaCache\" agent skill from https://github.com/ali-vilab/TeaCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ali-vilab-teacache\",\"task\":\"Install TeaCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review TeaCache trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add ali-vilab-teacache","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"TeaCache\" agent skill from https://github.com/ali-vilab/TeaCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ali-vilab-teacache\",\"task\":\"Install TeaCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"TeaCache\" as a Claude Code skill from https://github.com/ali-vilab/TeaCache. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ali-vilab-teacache\",\"task\":\"Install TeaCache\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"TeaCache\" from https://github.com/ali-vilab/TeaCache into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ali-vilab-teacache\",\"task\":\"Install TeaCache\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ali-vilab-teacache","name":"TeaCache","description":"Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model","category":"media-automation","url":"https://www.openagentskill.com/skills/ali-vilab-teacache","repository":"https://github.com/ali-vilab/TeaCache","github_repo":"ali-vilab/TeaCache"},"suited_tasks":["Design and creative workflows","general agent builders","teams that value GitHub adoption signals","Inspect visual requirements","Generate reusable assets","Package output for review","Turn a brief into a shot plan","Assign references and camera motion"],"suited_agents":["Python","Video Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ali-vilab/TeaCache","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add ali-vilab-teacache"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"TeaCache\" agent skill from https://github.com/ali-vilab/TeaCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ali-vilab-teacache\",\"task\":\"Install TeaCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"TeaCache\" as a Claude Code skill from https://github.com/ali-vilab/TeaCache. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ali-vilab-teacache\",\"task\":\"Install TeaCache\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"TeaCache\" from https://github.com/ali-vilab/TeaCache into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"ali-vilab-teacache\",\"task\":\"Install TeaCache\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/ali-vilab-teacache/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ali-vilab-teacache"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.4K GitHub stars","repoActivity":"1.4K stars, 60 forks","lastPushed":"1y since push","license":"Apache-2.0","repository":"https://github.com/ali-vilab/TeaCache","install":"npx skills add ali-vilab/TeaCache","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["media-automation","video-generation","creative","media","design","cogvideox"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":72,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":66,"label":"Promising"},"supply":{"track":"Design and creative production","scenario":"Design and creative","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push"],"agent_contract":{"task_input":"Use hunt-cache-poison","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 72/100 Needs review","Safety: 60/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"ali-vilab-teacache (TeaCache)","install_command":"npx skills add ali-vilab/TeaCache","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"ali-vilab-teacache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/ali-vilab-teacache","api":"https://www.openagentskill.com/api/agent/skills/ali-vilab-teacache","audit":"https://www.openagentskill.com/skills/ali-vilab-teacache/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ali-vilab-teacache&task=Use%20hunt-cache-poison&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ali-vilab-teacache/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ali-vilab-teacache"}},"use_cases":[{"slug":"design-creative","title":"Design and creative","url":"https://www.openagentskill.com/use-cases/design-creative"},{"slug":"video-creation","title":"Video creation","url":"https://www.openagentskill.com/use-cases/video-creation"},{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"}],"urls":{"web":"https://www.openagentskill.com/skills/ali-vilab-teacache","api":"https://www.openagentskill.com/api/agent/skills/ali-vilab-teacache","install_api":"https://www.openagentskill.com/api/skills/ali-vilab-teacache/install","audit":"https://www.openagentskill.com/skills/ali-vilab-teacache/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ali-vilab-teacache&task=Use%20hunt-cache-poison&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/ali-vilab-teacache?metric=audit","repository":"https://github.com/ali-vilab/TeaCache"}}],"blocked_candidates":[{"rank":5,"match_score":30,"raw_match_score":102.2,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"elementalsouls-hunt-cicd","name":"hunt-cicd","description":"Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable.","category":"security","github_stars":4083,"created_at":"2026-09-02T14:55:22.993166+00:00","updated_at":"2026-09-02T08:49:05+00:00","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd","github_repo":"elementalsouls/Claude-BugHunter","source_version":{"version":"1.0.0","commit_sha":"0efc24c3510d55bfef117d5594c0766df14f887b","content_hash":"4645e37a7695a36610ae3e86d8fc3f57b45fb8a56832aac7006cece481931bc2","ref":"main","path":"skills/hunt-cicd/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: hunt","Useful GitHub adoption: 4,083 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"security-compliance","title":"Security and compliance"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":4083,"starsLabel":"4.1K","forks":634,"license":"MIT","qualityScore":83,"trustScore":68,"auditScore":80},"maintenance":{"status":"fresh","label":"3d since push","daysSincePush":3,"lastPushedAt":"2026-09-02T08:49:05+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Dependency or permission surface needs review","Permission surface may require sandboxing","The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context.","Some commands (e.g., Jenkins script console RCE, file read) are inherently dangerous if executed against unauthorized targets; the skill relies on implied authorization but could be clearer.","Quality score needs review"]},"coverageTags":["Coding","GitHub automation","security","agent-skill"]},"quality":{"score":83,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"4.1K","tone":"positive"},{"label":"Freshness","value":"3d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context."]},"trust":{"version":"trust-score-v4","score":68,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection.","recommendedAction":"Inspect the repository, license, and recent activity before connecting it to agent workflows.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.1K stars, 634 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":54,"weight":0.12,"status":"warn","detail":"command execution surface, credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":36,"weight":0.07,"status":"fail","detail":"secrets or environment access, shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.1K stars, 634 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"warn","label":"Dependency/runtime risk","detail":"command execution surface, credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"fail","label":"Permission surface","detail":"secrets or environment access, shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution"],"evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 634 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Dependency/runtime risk: command execution surface, credential or environment access"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["security","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution"]},"trust_v5":{"version":"trust-score-v5","score":60,"base_score":68,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["60/100 Trust Score v5","68/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.1K stars, 634 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":54,"weight":0.12,"status":"warn","detail":"command execution surface, credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":36,"weight":0.07,"status":"fail","detail":"secrets or environment access, shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.1K stars, 634 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"warn","label":"Dependency/runtime risk","detail":"command execution surface, credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"fail","label":"Permission surface","detail":"secrets or environment access, shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 634 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Dependency/runtime risk: command execution surface, credential or environment access"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["security","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd","trust_score":60,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["security","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":68,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":80,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Dependency or permission surface needs review","Permission surface may require sandboxing","The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context.","Some commands (e.g., Jenkins script console RCE, file read) are inherently dangerous if executed against unauthorized targets; the skill relies on implied authorization but could be clearer.","Quality score needs review"]},"safety":{"score":40,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"blocked","label":"Blocked for auto-install","badge":"BLOCKED","summary":"This skill should not be selected by an agent without explicit human security review.","recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","auto_install_policy":"block","reasons":["Metadata combines secrets access with shell or command execution","High-risk permission hints: Shell or command execution, Secrets or environment access"]},"auto_install_allowed":false,"human_review_required":true,"blocked":true,"audit_risk":"needs_review","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"},{"id":"secrets","label":"Secrets or environment access","reason":"Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.","severity":"high"}],"policy_warnings":["High-risk permission hints: Shell or command execution, Secrets or environment access","Dependency or permission surface needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"blocked","label":"Blocked for auto-install","badge":"BLOCKED","auto_install_policy":"block","auto_install_allowed":false,"human_review_required":true,"blocked":true,"recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","reasons":["Metadata combines secrets access with shell or command execution","High-risk permission hints: Shell or command execution, Secrets or environment access"]},"decision":{"readiness_score":94,"readiness_label":"Production-ready","headline":"Primary pick for GitHub automation","role":"Primary pick","best_for":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context.","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd","value":"Install the \"hunt-cicd\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cicd\",\"task\":\"Install hunt-cicd\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review hunt-cicd trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add elementalsouls-hunt-cicd","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"hunt-cicd\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cicd\",\"task\":\"Install hunt-cicd\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"hunt-cicd\" as a Claude Code skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cicd\",\"task\":\"Install hunt-cicd\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"hunt-cicd\" from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cicd\",\"task\":\"Install hunt-cicd\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"elementalsouls-hunt-cicd","name":"hunt-cicd","description":"Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable.","category":"security","url":"https://www.openagentskill.com/skills/elementalsouls-hunt-cicd","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd","github_repo":"elementalsouls/Claude-BugHunter"},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect risky files","Prioritize findings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add elementalsouls-hunt-cicd"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"hunt-cicd\" agent skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cicd\",\"task\":\"Install hunt-cicd\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"hunt-cicd\" as a Claude Code skill from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cicd\",\"task\":\"Install hunt-cicd\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"hunt-cicd\" from https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"elementalsouls-hunt-cicd\",\"task\":\"Install hunt-cicd\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-cicd/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/elementalsouls-hunt-cicd"},"trust":{"score":68,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"4.1K GitHub stars","repoActivity":"4.1K stars, 634 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd","install":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["security","agent-skill"],"known_risks":["The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Dependency/runtime risk: command execution surface, credential or environment access","Permission surface: secrets or environment access, shell or command execution"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":80,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Dependency or permission surface needs review","Permission surface may require sandboxing","The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context.","Some commands (e.g., Jenkins script console RCE, file read) are inherently dangerous if executed against unauthorized targets; the skill relies on implied authorization but could be clearer.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Dependency/runtime risk: command execution surface, credential or environment access"]},"safety_gate":{"tier":"blocked","label":"Blocked for auto-install","auto_install_policy":"block","auto_install_allowed":false,"human_review_required":true,"blocked":true,"recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first."},"quality":{"score":83,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3d since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The skill does not explicitly state that it must only be used on systems the user is authorized to test, which could lead to misuse if adopted without proper context.","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution, Secrets or environment access","Dependency or permission surface needs review","Permission surface may require sandboxing","Some commands (e.g., Jenkins script console RCE, file read) are inherently dangerous if executed against unauthorized targets; the skill relies on implied authorization but could be clearer."],"agent_contract":{"task_input":"Use hunt-cache-poison","recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","install_policy":"block","minimum_review_before_use":["Trust: 68/100 Manual review","Audit: 80/100 Needs review","Safety: 40/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"elementalsouls-hunt-cicd (hunt-cicd)","install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cicd","risk_summary":"Needs review; Blocked for auto-install; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"elementalsouls-hunt-cicd","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/elementalsouls-hunt-cicd","api":"https://www.openagentskill.com/api/agent/skills/elementalsouls-hunt-cicd","audit":"https://www.openagentskill.com/skills/elementalsouls-hunt-cicd/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=elementalsouls-hunt-cicd&task=Use%20hunt-cache-poison&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-cicd/install","manifest":"https://www.openagentskill.com/api/registry/manifest/elementalsouls-hunt-cicd"}},"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"security-compliance","title":"Security and compliance","url":"https://www.openagentskill.com/use-cases/security-compliance"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/elementalsouls-hunt-cicd","api":"https://www.openagentskill.com/api/agent/skills/elementalsouls-hunt-cicd","install_api":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-cicd/install","audit":"https://www.openagentskill.com/skills/elementalsouls-hunt-cicd/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=elementalsouls-hunt-cicd&task=Use%20hunt-cache-poison&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/elementalsouls-hunt-cicd?metric=audit","repository":"https://github.com/elementalsouls/Claude-BugHunter/tree/main/skills/hunt-cicd"}}],"agent_workflow":{"mode":"resolve_review_install","recommended_action":"Require human approval before installing into a real workspace.","selected_skill":{"slug":"zilliztech-gptcache","name":"GPTCache","url":"https://www.openagentskill.com/skills/zilliztech-gptcache","repository":"https://github.com/zilliztech/GPTCache"},"install":{"target":"codex","label":"Codex install prompt","kind":"agent-prompt","command":"npx skills add zilliztech/GPTCache","value":"Install the \"GPTCache\" agent skill from https://github.com/zilliztech/GPTCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","api":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install"},"copy_paste_prompt":"Task: Use hunt-cache-poison\nUse GPTCache from https://www.openagentskill.com/skills/zilliztech-gptcache.\nReview the audit first: https://www.openagentskill.com/skills/zilliztech-gptcache/audit\nReview the eval first: https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/zilliztech-gptcache/install\nInstall command: npx skills add zilliztech/GPTCache\nIf audit or policy warnings look unsafe for this workspace, use one of the alternatives instead.","api_sequence":[{"step":1,"label":"Resolve task","method":"GET","url":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","skill_slug":"zilliztech-gptcache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}}}],"review_checklist":["Safety tier: Reviewed with permission notes","Safety score: 62/100 Review before install","Audit score: 74/100 Needs review","Trust score: 71/100 Sandbox only","Readiness: 79/100 Strong shortlist","Documentation summary is thin","Documentation summary is thin","Repository appears stale","Repository looks stale"],"fallback_strategy":[{"slug":"elementalsouls-hunt-cache-poison","name":"hunt-cache-poison","reason":"Matches task terms: hunt, cache, poison","url":"https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison","install_api":"https://www.openagentskill.com/api/skills/elementalsouls-hunt-cache-poison/install"},{"slug":"cnighswonger-claude-code-cache-fix","name":"Claude Code Cache Fix","reason":"Matches task terms: cache","url":"https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix","install_api":"https://www.openagentskill.com/api/skills/cnighswonger-claude-code-cache-fix/install"},{"slug":"hackmanit-web-cache-vulnerability-scanner","name":"Web Cache Vulnerability Scanner","reason":"Matches task terms: cache","url":"https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner","install_api":"https://www.openagentskill.com/api/skills/hackmanit-web-cache-vulnerability-scanner/install"}],"expected_agent_output":{"selected_skill":"slug and name","install_command":"command or agent prompt used","risk_summary":"audit, trust, and policy notes","next_step":"what the agent will do after install","outcome_event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5"}},"agent_handoff":{"version":"openagentskill-agent-handoff-v1","mode":"resolve_compare_review_install","task":"Use hunt-cache-poison","agent":"codex","selected_skill":{"slug":"zilliztech-gptcache","name":"GPTCache","url":"https://www.openagentskill.com/skills/zilliztech-gptcache","api_url":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache","audit_url":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium","repository":"https://github.com/zilliztech/GPTCache"},"install_plan":{"command":"npx skills add zilliztech/GPTCache","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"GPTCache\" agent skill from https://github.com/zilliztech/GPTCache. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Semantic cache for LLMs. Fully integrated with LangChain and llama_index. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zilliztech-gptcache\",\"task\":\"Install GPTCache\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","install_api":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install","auto_install_allowed":false,"human_review_required":true,"policy":"review"},"api_sequence":[{"step":1,"label":"Resolve task","method":"GET","url":"https://www.openagentskill.com/api/agent/resolve?task=Use%20hunt-cache-poison&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/zilliztech-gptcache/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","skill_slug":"zilliztech-gptcache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}}}],"platform_templates":[{"id":"codex","name":"Codex","surface":"Coding agent / local workspace","copy_prompt":"Task: Use hunt-cache-poison\nSelected skill: GPTCache (zilliztech-gptcache)\nSkill URL: https://www.openagentskill.com/skills/zilliztech-gptcache\nAudit URL: https://www.openagentskill.com/skills/zilliztech-gptcache/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/zilliztech-gptcache/install\nInstall command: npx skills add zilliztech/GPTCache\nInstall policy: Human review is required before install.\nOutcome feedback: use install_receipt.outcome_feedback.event_id or feedback.event_id from the Resolve API and report the result to /api/agent/outcome after one narrow run. Include outcome, install_used, task_success, output_quality, workspace, error_type, and human_review_required when known.\n\nBefore installing:\n1. Read the audit and eval result.\n2. Report risk notes and files or commands that will be touched.\n3. Install only in a sandbox or low-risk workspace first.\n4. If risk is unacceptable, use an alternative.\n\nAlternatives:\n- hunt-cache-poison (elementalsouls-hunt-cache-poison): https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison\n- Claude Code Cache Fix (cnighswonger-claude-code-cache-fix): https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix\n- Web Cache Vulnerability Scanner (hackmanit-web-cache-vulnerability-scanner): https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner\n\nExpected Codex output:\n- selected_skill\n- install_command\n- risk_summary\n- outcome_event_id\n- alternatives\n- files_or_commands_to_touch\n- next_action"},{"id":"claude-code","name":"Claude Code","surface":"Claude Code skill workflow","copy_prompt":"Task: Use hunt-cache-poison\nSelected skill: GPTCache (zilliztech-gptcache)\nSkill URL: https://www.openagentskill.com/skills/zilliztech-gptcache\nAudit URL: https://www.openagentskill.com/skills/zilliztech-gptcache/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/zilliztech-gptcache/install\nInstall command: npx skills add zilliztech/GPTCache\nInstall policy: Human review is required before install.\nOutcome feedback: use install_receipt.outcome_feedback.event_id or feedback.event_id from the Resolve API and report the result to /api/agent/outcome after one narrow run. Include outcome, install_used, task_success, output_quality, workspace, error_type, and human_review_required when known.\n\nBefore installing:\n1. Read the audit and eval result.\n2. Report risk notes and files or commands that will be touched.\n3. Install only in a sandbox or low-risk workspace first.\n4. If risk is unacceptable, use an alternative.\n\nAlternatives:\n- hunt-cache-poison (elementalsouls-hunt-cache-poison): https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison\n- Claude Code Cache Fix (cnighswonger-claude-code-cache-fix): https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix\n- Web Cache Vulnerability Scanner (hackmanit-web-cache-vulnerability-scanner): https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner\n\nExpected Claude Code output:\n- selected_skill\n- skill_files_or_instructions\n- install_prompt\n- risk_summary\n- outcome_event_id\n- activation_steps\n- fallback_skill"},{"id":"cursor","name":"Cursor","surface":"Cursor rules / agent instructions","copy_prompt":"Task: Use hunt-cache-poison\nSelected skill: GPTCache (zilliztech-gptcache)\nSkill URL: https://www.openagentskill.com/skills/zilliztech-gptcache\nAudit URL: https://www.openagentskill.com/skills/zilliztech-gptcache/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=zilliztech-gptcache&task=Use%20hunt-cache-poison&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/zilliztech-gptcache/install\nInstall command: npx skills add zilliztech/GPTCache\nInstall policy: Human review is required before install.\nOutcome feedback: use install_receipt.outcome_feedback.event_id or feedback.event_id from the Resolve API and report the result to /api/agent/outcome after one narrow run. Include outcome, install_used, task_success, output_quality, workspace, error_type, and human_review_required when known.\n\nBefore installing:\n1. Read the audit and eval result.\n2. Report risk notes and files or commands that will be touched.\n3. Install only in a sandbox or low-risk workspace first.\n4. If risk is unacceptable, use an alternative.\n\nAlternatives:\n- hunt-cache-poison (elementalsouls-hunt-cache-poison): https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison\n- Claude Code Cache Fix (cnighswonger-claude-code-cache-fix): https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix\n- Web Cache Vulnerability Scanner (hackmanit-web-cache-vulnerability-scanner): https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner\n\nExpected Cursor output:\n- selected_skill\n- cursor_rule_or_prompt\n- install_command\n- risk_summary\n- outcome_event_id\n- when_to_use\n- when_not_to_use"}],"review_checklist":["Safety tier: Reviewed with permission notes","Safety score: 62/100 Review before install","Audit score: 74/100 Needs review","Trust score: 71/100 Sandbox only","Readiness: 79/100 Strong shortlist","Documentation summary is thin","Documentation summary is thin","Repository appears stale","Repository looks stale"],"expected_output":{"selected_skill":"slug and name","install_command":"command or agent prompt used","risk_summary":"audit, trust, and policy notes","next_step":"what the agent will do after install","outcome_event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5"},"feedback":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","outcome_api":"https://www.openagentskill.com/api/agent/outcome","cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5\" --skill \"zilliztech-gptcache\" --task \"Use hunt-cache-poison\" --agent \"codex\" --outcome success","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"]},"blocked_actions":["Do not install when safety_gate.blocked is true.","Do not install when the audit or eval reports unacceptable workspace risk.","Do not execute shell commands, access secrets, or call external services without user approval.","Do not keep the skill as an always-on instruction if it only fits a narrow task."]},"policy_decision":{"status":"human_review_required","summary":"Require human approval before installing into a real workspace."},"agent_decision":{"input_task":"Use hunt-cache-poison","recommended_skill":{"slug":"zilliztech-gptcache","name":"GPTCache","url":"https://www.openagentskill.com/skills/zilliztech-gptcache","audit_url":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit","repository":"https://github.com/zilliztech/GPTCache","safety_tier":"Reviewed with permission notes","auto_install_policy":"review"},"alternative_skills":[{"slug":"elementalsouls-hunt-cache-poison","name":"hunt-cache-poison","url":"https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison","install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","why_consider":"Matches task terms: hunt, cache, poison","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"57/100 Review before install","trust":"68/100 Manual review","notes":["High-risk permission hints: Secrets or environment access","Permission surface may require sandboxing","SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Description mentions 10 public bug bounty reports but report_count is 8 - inconsistency.","No explicit statement about only testing on authorized targets, though implied by bug bounty context."]}},{"slug":"cnighswonger-claude-code-cache-fix","name":"Claude Code Cache Fix","url":"https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix","install_command":"npx skills add cnighswonger/claude-code-cache-fix","why_consider":"Matches task terms: cache","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"50/100 Avoid automatic install","trust":"70/100 Manual review","notes":["High-risk permission hints: Shell or command execution","License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata"]}},{"slug":"hackmanit-web-cache-vulnerability-scanner","name":"Web Cache Vulnerability Scanner","url":"https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner","install_command":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","why_consider":"Matches task terms: cache","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"54/100 Avoid automatic install","trust":"79/100 Strong shortlist","notes":["High-risk permission hints: Shell or command execution","Quality score needs review","Documentation summary is thin"]}}],"install_command":"npx skills add zilliztech/GPTCache","install_target":"Codex install prompt","why_recommended":["Matches task terms: cache","Useful GitHub adoption: 8,067 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30","Companion skill for RAG and knowledge"],"risk_summary":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"62/100 Review before install","trust":"79/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","action":"Require human approval before installing into a real workspace."},"feedback":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","outcome_api":"https://www.openagentskill.com/api/agent/outcome","cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5\" --skill \"zilliztech-gptcache\" --task \"Use hunt-cache-poison\" --agent \"codex\" --outcome success","contract":{"version":"openagentskill-agent-feedback-loop-v3","status":"active","purpose":"Report the result of one resolved skill run so Trust Score v5 and future Resolve rankings learn from real use.","event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","selected_skill_slug":"zilliztech-gptcache","selected_skill_name":"GPTCache","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","idempotency":"Retrying the same event_id updates the previous outcome.","dry_run":{"supported":true,"instruction":"Set dry_run=true to validate a payload before wiring a new agent integration."},"expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"error_types":["install_failed","runtime_error","not_relevant","permission_blocked","risk_blocked","setup_required","low_quality_output","missing_dependency","timeout","other"],"workspaces":["sandbox","local","ci","production","unknown"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url"],"payload_template":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","skill_slug":"zilliztech-gptcache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5\" --skill \"zilliztech-gptcache\" --task \"Use hunt-cache-poison\" --agent \"codex\" --outcome success","ranking_inputs_updated":["Trust Score v5 outcome confidence","Resolve ranking outcome evidence","Skill detail outcome signal block","Outcome leaderboard"]}},"agent_next_steps":["Read the audit URL before installing.","Ask for human approval before installing.","Use install command: npx skills add zilliztech/GPTCache","After one narrow task, report the outcome with: npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5\" --skill \"zilliztech-gptcache\" --task \"Use hunt-cache-poison\" --agent \"codex\" --outcome success","Summarize output, warnings, files touched, and whether setup or human review was required."]},"decision_packet":{"version":"openagentskill-agent-decision-packet-v1","task":"Use hunt-cache-poison","agent":"codex","selected_skill":{"slug":"zilliztech-gptcache","name":"GPTCache","url":"https://www.openagentskill.com/skills/zilliztech-gptcache","api_url":"https://www.openagentskill.com/api/agent/skills/zilliztech-gptcache","audit_url":"https://www.openagentskill.com/skills/zilliztech-gptcache/audit","repository":"https://github.com/zilliztech/GPTCache","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"suited_tasks":["RAG and knowledge workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","LangChain"],"install":{"command":"npx skills add zilliztech/GPTCache","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":71,"label":"Sandbox only","version":"trust-score-v5","base_score":79,"outcome_confidence":0,"decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["71/100 Trust Score v5","79/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"status":"pass","detail":"8.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"status":"pass","detail":"8.1K stars, 583 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"status":"pass","detail":"npx skills add zilliztech/GPTCache"},{"id":"install_safety","label":"Install command safety","score":92,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"status":"pass","detail":"https://github.com/zilliztech/GPTCache"},{"id":"review_status","label":"Review status","score":88,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"status":"info","detail":"No agent outcome data yet"}]},"risk":{"level":"Needs review","audit_label":"Needs review","safety":"62/100 Review before install","trust":"79/100 Strong shortlist","safety_tier":"Reviewed with permission notes","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 74/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"elementalsouls-hunt-cache-poison","name":"hunt-cache-poison","url":"https://www.openagentskill.com/skills/elementalsouls-hunt-cache-poison","install_command":"npx skills add elementalsouls/Claude-BugHunter --skill hunt-cache-poison","trust_score":68,"audit_score":81,"safety_score":57,"why_consider":"Matches task terms: hunt, cache, poison","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"57/100 Review before install","trust":"68/100 Manual review","notes":["High-risk permission hints: Secrets or environment access","Permission surface may require sandboxing","SKILL.md excerpt appears truncated at 'Send two identical' - verify full content is complete.","Description mentions 10 public bug bounty reports but report_count is 8 - inconsistency.","No explicit statement about only testing on authorized targets, though implied by bug bounty context."]}},{"slug":"cnighswonger-claude-code-cache-fix","name":"Claude Code Cache Fix","url":"https://www.openagentskill.com/skills/cnighswonger-claude-code-cache-fix","install_command":"npx skills add cnighswonger/claude-code-cache-fix","trust_score":70,"audit_score":74,"safety_score":50,"why_consider":"Matches task terms: cache","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"50/100 Avoid automatic install","trust":"70/100 Manual review","notes":["High-risk permission hints: Shell or command execution","License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 308 stars, 22 forks; issue activity unavailable in current metadata"]}},{"slug":"hackmanit-web-cache-vulnerability-scanner","name":"Web Cache Vulnerability Scanner","url":"https://www.openagentskill.com/skills/hackmanit-web-cache-vulnerability-scanner","install_command":"npx skills add Hackmanit/Web-Cache-Vulnerability-Scanner","trust_score":79,"audit_score":78,"safety_score":54,"why_consider":"Matches task terms: cache","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"54/100 Avoid automatic install","trust":"79/100 Strong shortlist","notes":["High-risk permission hints: Shell or command execution","Quality score needs review","Documentation summary is thin"]}},{"slug":"ali-vilab-teacache","name":"TeaCache","url":"https://www.openagentskill.com/skills/ali-vilab-teacache","install_command":"npx skills add ali-vilab/TeaCache","trust_score":79,"audit_score":72,"safety_score":60,"why_consider":"Matches task terms: cache","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"60/100 Review before install","trust":"79/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]}}],"outcome_feedback":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5","skill_slug":"zilliztech-gptcache","task":"Use hunt-cache-poison","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_01af834b-cbf7-45d6-9db1-075f463f40a5\" --skill \"zilliztech-gptcache\" --task \"Use hunt-cache-poison\" --agent \"codex\" --outcome success"},"next_agent_action":"Ask for human approval or choose a safer alternative before installing.","stable_fields":["decision_packet.selected_skill","decision_packet.install","decision_packet.risk.do_not_use_when","decision_packet.alternatives","decision_packet.outcome_feedback","decision_packet.trust.decision"]},"benchmark":{"endpoint":"https://www.openagentskill.com/api/agent/evals","note":"Use the evals endpoint to regression-test recommendation quality before changing ranking logic."},"meta":{"endpoint":"/api/agent/resolve","api_version":"2.0","generated_at":"2026-09-05T09:44:32.958Z","total_skills_searched":906,"total_candidates":15,"candidate_pool":{"sort":"quality","size":906,"note":"Resolver searches the highest-quality candidate pool for low-latency agent use. Browse /skills for the full public index."},"contract":{"best_skill":"recommendation.best_skill","install":"recommendation.install","why":"recommendation.why_recommended","risk":"recommendation.risk","alternatives":"recommendation.alternatives","agent_handoff":"agent_handoff.platform_templates + agent_handoff.review_checklist","decision_packet":"decision_packet","install_receipt":"install_receipt","recommendation_lanes":"recommendation_lanes"}}}