{"slug":"gaasher-purple-team","name":"purple-team","description":"Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure classes against the frozen target, blue patches the target to close them under a regression gate, then a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only find, or blue-team alone to only fix.","long_description":"---\nname: purple-team\ndescription: >\n Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or\n API they own by running attack and defense together as a closed loop, not just one or the other. It\n orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure\n classes against the frozen target, blue patches the target to close them under a regression gate, then\n a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix\n introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is\n hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking\n a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only\n find, or blue-team alone to only fix.\ncompatibility: >\n Requires Python 3.9+ and the sibling red-team + blue-team skills installed. Real isolated subagents on\n Claude Code; runs the phases inline (serial) elsewhere. git + gh CLI for the PR handoff (degrades).\nmetadata:\n version: \"0.1.0\"\n---\n\n# Purple Team\n\nThe **combined red+blue** loop — the outer orchestration the `red-team` skill says \"lives outside it.\"\nThe artifact is a target system (frozen *within* a phase, patched *between* phases); the feedback signal\nis **how many new failure classes a fresh attack pass finds against the patched target**. Each cycle\nruns three strictly separated phases — **find** (red-team), **fix** (blue-team), **re-verify** (a fresh\nred-team pass) — and you repeat until a fresh find stays **dry** (zero new classes), meaning the target\nis hardened. Red and blue run as **independent agents** so the attacker that wrote a catalogue never\ngrades its own patch. On stop it opens a pull request with the cycle history and the patch set.\n\n## When to use\nUse to harden a guardrail/classifier/filter/prompt/API the user owns or is authorized to test, when the\ngoal is an actually-hardened target plus a reviewable patch — not just a catalogue (that is `red-team`\nalone) and not just closing a pre-existing catalogue (that is `blue-team` alone). It needs a runnable\noracle for the objective signal, and the two sibling skills installed.\n\nDefault: spawn red and blue as separate subagents per phase. Escape hatch: on hosts without subagent\ndispatch, run each phase inline (serial) per the role files — still correct, but the same context plays\nboth sides, so be deliberate about not letting the fix bias the re-verify. Not for unauthorized targets.\n\n## Setup\nResolve bindings interactively. If `loop.run.yaml` exists, load it, confirm the values in one line, and\nskip to the loop. Otherwise: on Claude Code (the `AskUserQuestion` tool is available) infer a likely\nvalue per binding and recommend it; on other hosts ask each as a quoted prompt. Then write\n`loop.run.yaml` (format: `examples/run.example.yaml`) and confirm before creating any other files.\n\nThe phases reuse the sibling skills, so the bindings are their union — one shared `loop.run.yaml` drives\nboth. The same file is `` to blue (writable) and the program behind `` to red\n(read-only); the same path is red's `` and blue's ``.\n\n| binding | meaning | default | how to infer |\n|---|---|---|---|\n| `` | run the target on one stdin input → a verdict (what red attacks) | — | the guardrail/classifier/API entrypoint |\n| `` | the source file(s) blue may edit to fix the target | — | the file(s) behind `` |\n| `` | ground-truth verdict for the same input (frozen) | — | a reference checker / policy impl |\n| `` | functional tests that must stay green through a fix (exits 0) | — | the target's test command; else rely on `` |\n| `` | benign + clearly-correct inputs blue must not break | `/holdout.jsonl` | known-good inputs the oracle agrees on |\n| `` | shared failures file: red writes it, blue closes it, JSONL `{id,text,class,...}` | `/failures.jsonl` | — |\n| `` | `branches` (commit per fix → PR) or `snapshots` | `branches` | dirty/non-git tree → snapshots |\n| `` | branch the fixes land on and the PR opens from | `purple-team/` | today's date as `` |\n| `` | where catalogues, snapshots, ledgers live | `./sandbox` | — |\n| `` | max find→fix→re-verify cycles | 4 | — |\n| ``, `` | inner per-phase budgets passed to red / blue | 8 | — |\n\n`` is this skill's installed folder. The phases run the sibling skills' tools\n(`red-team/tools/harness.py`, `blue-team/tools/verify.py`); the role files name them.\n\n## The loop\nCopy this checklist and tick items off each cycle. Cycles are numbered from 0; per-cycle artifacts go in\n`` with the cycle index in the name so nothing is overwritten: the find catalogue is\n`failures.cycle.jsonl` (cycle 0 may use `` directly) and the re-verify result is\n`failures.cycle_reverify.jsonl`. The **catalogue blue fixes in cycle N is the failures file from that\ncycle's find/re-verify pass** — never append back into one shared file, so each cycle's accounting is clean.\n\n- [ ] **Cycle 0 — Find.** Run the **red-team** phase against the **frozen** target (spawn-or-degrade,\n `roles/red-find.md`), writing `failures.cycle0.jsonl`. Read back its distinct failure classes.\n- [ ] If the catalogue is empty on cycle 0, **stop** — the target is already dry; report clean, no PR.\n- [ ] **Fix.** Run the **blue-team** phase on this cycle's failures file (spawn-or-degrade,\n `roles/blue-fix.md`): it patches `` one class per iteration under the gate +\n regression guard, committing kept fixes on ``. Read back the classes it **closed** and\n any **residuals**.\n- [ ] **Re-verify.** Run a **fresh** red-team phase against the **patched** target into\n `failures.cycle_reverify.jsonl`. This confirms the closed classes no longer reproduce and\n surfaces any **new** classes the fix introduced (e.g. an over-block).\n- [ ] Append one cycle row to the ledger. If the re-verify pass found new classes, they become the\n **next** cycle's catalogue (`failures.cycle.jsonl`) — loop to **Find/Fix** for cycle N+1.\n Repeat **find→fix→re-verify** until a re-verify pass stays **dry** (no new classes) or\n `` is hit.\n- [ ] **Handoff.** Open the pull request with the full cycle history (see\n [Handoff](#handoff-the-pull-request)).\n\n**Phase independence (why three separated phases).** The target is read-only ground truth for the\nduration of a red pass, so patches happen only *between* passes — mutating it mid-pass would break\nreproducibility and the class accounting. Spawn red and blue as **separate** subagents so neither grades\nits own work; the orchestrator only passes artifacts (the catalogue, the closed/residual summary)\nbetween them. Launch a phase's subagent and wait for its structured return before the next phase.\n\n## Ledger\n`/cycle_ledger.tsv`, tab-separated, never commas in free text. Header\n`cycle\tfound\tfixed\tresidual\tregressions_introduced\tnet_open`:\n```\ncycle\tfound\tfixed\tresidual\tregressions_introduced\tnet_open\n0\t5\t5\t0\t1\t1\n1\t1\t1\t0\t0\t0\n```\nAll counts are **distinct classes**, not inner iterations: `found` = classes red surfaced this cycle;\n`fixed` = classes blue *closed* (a class blue attempted several times still counts once); `residual` =\nclasses blue could not close; `regressions_introduced` = new classes the re-verify pass found that the\nfix caused; `net_open` = classes still open entering the next cycle (`residual + regressions_introduced`,\nthe next cycle's catalogue size). Convergence is a re-verify pass with `net_open` = 0. Report the cycle\nat which the target went dry (or the best `net_open` reached).\n\n## Constraints\n- **Authorized targets only.** This drives real attacks against the target; only run it on a system the\n user owns or is explicitly authorized to test (inherited from red-team).\n- **Keep the phases independent and the ground truth frozen.** Never let one phase edit the oracle,\n `` tests, ``, or either tool; never patch the target inside a red pass. These keep\n the find/fix/re-verify accounting honest.\n- **Re-verify is a *fresh* attack, not a replay.** It must be free to find new classes (including ones\n the fix introduced), not just re-check the old list — concretely, at least half its candidates should\n be new payloads and it should try at least two attack angles not in the prior catalogue (this matters\n most in degrade mode, where the same context plays both sides). That is what makes the loop converge to dry\n rather than to \"the original five are gone.\"\n- **One change per inner iteration** (handled by the sub-loops); the orchestrator changes nothing\n itself except moving artifacts between phases.\n- Stay inside the repo and ``; do not pause between phases to ask whether to continue —\n run until dry or ``.\n\n## Handoff: the pull request\nThe deliverable is one **pull request** for the whole hardening run — the communication interface to the\ntarget's owner, who keeps final approval. With the tree at blue's best state and the kept fixes already\ncommitted on ``:\n- Open it with `gh pr create`; body = the cycle ledger (found → fixed → re-verified per cycle), one\n reproducible example per closed class, and any residuals still open. **Confirm once before opening** —\n it is outward-facing; never auto-push silently.\n- **Degrade, don't fail:** with no remote / no `gh`, leave commits on `` and write\n `git format-patch` + `PR_BODY.md` into ``; in `snapshots` mode emit a unified diff +\n `PR_BODY.md`. Tell the user the one command to open the PR themselves.\n\n## Roles\n- `roles/red-find.md` — runs the red-team phase against the target and returns the catalogue + classes.\n- `roles/blue-fix.md` — runs the blue-team phase on the catalogue and returns closed classes + residuals.\n\nBoth are **spawn-or-degrade**: spawn a real isolated subagent on Claude Code (the `Agent`/Task tool),\nelse adopt the role inline. Each delegates to the sibling skill (`red-team` / `blue-team`) bound to the\nshared `loop.run.yaml`; if a sibling is not installed, ask the user to install it (`npx skills add\ngaasher/agent-loop-skills`) rather than re-implementing it here.\n","tagline":"Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds d","category":"coding-agents","tags":["agent-skill"],"author":"gaasher","verified":false,"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"github fast track","sourceDetail":"gaasher/Agent-Loop-Skills","creatorName":"gaasher","creatorUrl":"https://github.com/gaasher","sourceUrl":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/gaasher-purple-team#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":163,"forks":19,"verified_installs":0,"successful_runs":0,"total_outcomes":0,"rating":0,"review_count":0,"quality_score":35.6},"quality":{"score":63,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"163","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v5","score":67,"base_score":75,"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":["67/100 Trust Score v5","75/100 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":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow 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 gaasher/Agent-Loop-Skills --skill purple-team"},{"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":48,"weight":0.07,"status":"warn","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team"},{"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":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface, network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"warn","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team"},{"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":["Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team","install":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","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","2mo 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","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document 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":["coding-agents","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","trust_score":67,"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":["coding-agents","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","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"trust_score_v5":{"version":"trust-score-v5","score":67,"base_score":75,"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":["67/100 Trust Score v5","75/100 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":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow 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 gaasher/Agent-Loop-Skills --skill purple-team"},{"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":48,"weight":0.07,"status":"warn","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team"},{"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":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface, network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"warn","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team"},{"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":["Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team","install":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","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","2mo 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","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document 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":["coding-agents","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","trust_score":67,"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":["coding-agents","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","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"trust_score_v4":{"version":"trust-score-v4","score":75,"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":62,"weight":0.13,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow 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 gaasher/Agent-Loop-Skills --skill purple-team"},{"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":48,"weight":0.07,"status":"warn","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team"},{"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":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface, network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"warn","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team"},{"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":["Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team","install":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","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","2mo since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document 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":["coding-agents","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","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document 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"]},"outcome_stats":null,"safety":{"score":48,"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","48/100 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"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","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,"blocked":false,"human_review_required":true,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["High-risk permission hints: Shell or command execution","48/100 agent safety score"]},"eval":{"version":"openagentskill-skill-eval-v1","status":"failed","score":69,"risk_level":"high","decision":{"recommendation":"do_not_auto_install","reason":"Permission surface: shell or command execution, filesystem or document access","auto_install_allowed":false,"policy":"block","human_review_required":true},"blockers":["Permission surface: shell or command execution, filesystem or document access"],"warnings":["Trust score: Good trust signals with a few areas worth checking before rollout.","Audit score: Needs review","Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","High-risk permission hints: Shell or command execution","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"],"validation_plan":["Inspect repository, README/SKILL.md, license, and recent commits before production use.","Install in an isolated workspace or sandbox with no production secrets available.","Run the smallest representative task and record files touched, commands run, network access, and outputs.","Compare the selected skill against at least one alternative when the eval status is review or failed.","Promote only after the agent reports a successful verification result and unresolved warnings are accepted."],"checks":[{"id":"task_fit","label":"Task fit","status":"pass","score":94,"required_for_auto_install":true,"detail":"Task wording matches this skill metadata.","evidence":["Evaluate purple-team before installing it in an agent workflow","coding-agents","Coding agents workflows; Claude Code teams; builders willing to evaluate younger projects"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add gaasher/Agent-Loop-Skills --skill purple-team"]},{"id":"install_safety","label":"Install command safety","status":"pass","score":92,"required_for_auto_install":true,"detail":"standard package or runtime install path","evidence":["npx skills add gaasher/Agent-Loop-Skills --skill purple-team"]},{"id":"trust_score","label":"Trust score","status":"warn","score":75,"required_for_auto_install":true,"detail":"Good trust signals with a few areas worth checking before rollout.","evidence":["Strong shortlist","163 GitHub stars","MIT"]},{"id":"audit_score","label":"Audit score","status":"warn","score":76,"required_for_auto_install":true,"detail":"Needs review","evidence":["Permission surface may require sandboxing"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"warn","score":48,"required_for_auto_install":true,"detail":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","evidence":["Test manually in an isolated workspace and compare against safer alternatives.","High-risk permission hints: Shell or command execution"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"pass","score":86,"required_for_auto_install":false,"detail":"Metadata includes enough usage and workflow context","evidence":["Strong README/SKILL.md context"]},{"id":"license_clarity","label":"License clarity","status":"pass","score":86,"required_for_auto_install":true,"detail":"MIT","evidence":["MIT"]},{"id":"recent_maintenance","label":"Recent maintenance","status":"pass","score":88,"required_for_auto_install":false,"detail":"2mo since push","evidence":["2mo since push"]},{"id":"permission_surface","label":"Permission surface","status":"fail","score":48,"required_for_auto_install":true,"detail":"shell or command execution, filesystem or document access","evidence":["Shell or command execution: high","Network access: medium","Filesystem access: medium"]},{"id":"alternatives","label":"Alternatives available","status":"info","score":55,"required_for_auto_install":false,"detail":"No close alternatives were found in the current shortlist.","evidence":[]}],"endpoints":{"web":"https://www.openagentskill.com/skills/gaasher-purple-team/evals","api":"/api/agent/evals?slug=gaasher-purple-team","text":"/api/agent/evals?slug=gaasher-purple-team&format=text"}},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"gaasher-purple-team","name":"purple-team","description":"Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure classes against the frozen target, blue patches the target to close them under a regression gate, then a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only find, or blue-team alone to only fix.","category":"coding-agents","url":"https://www.openagentskill.com/skills/gaasher-purple-team","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team","github_repo":"gaasher/Agent-Loop-Skills"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","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 gaasher-purple-team"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"purple-team\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team. 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: Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure classes against the frozen target, blue patches the target to close them under a regression gate, then a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only find, or blue-team alone to only fix. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-purple-team\",\"task\":\"Install purple-team\",\"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 \"purple-team\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team. 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: Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure classes against the frozen target, blue patches the target to close them under a regression gate, then a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only find, or blue-team alone to only fix. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-purple-team\",\"task\":\"Install purple-team\",\"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 \"purple-team\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team 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: Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure classes against the frozen target, blue patches the target to close them under a regression gate, then a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only find, or blue-team alone to only fix. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-purple-team\",\"task\":\"Install purple-team\",\"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/gaasher-purple-team/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/gaasher-purple-team"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team","install":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","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","agent-skill"],"known_risks":["Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document 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":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document 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":63,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo 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","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use purple-team in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 48/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gaasher-purple-team (purple-team)","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","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":"","skill_slug":"gaasher-purple-team","task":"Use purple-team in an agent workflow","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/gaasher-purple-team","api":"https://www.openagentskill.com/api/agent/skills/gaasher-purple-team","audit":"https://www.openagentskill.com/skills/gaasher-purple-team/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-purple-team&task=Use%20purple-team%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20purple-team%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20purple-team%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/gaasher-purple-team/install","manifest":"https://www.openagentskill.com/api/registry/manifest/gaasher-purple-team"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"gaasher-purple-team","name":"purple-team","description":"Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure classes against the frozen target, blue patches the target to close them under a regression gate, then a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only find, or blue-team alone to only fix.","category":"coding-agents","url":"https://www.openagentskill.com/skills/gaasher-purple-team","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team","github_repo":"gaasher/Agent-Loop-Skills"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","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 gaasher-purple-team"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"purple-team\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team. 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: Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure classes against the frozen target, blue patches the target to close them under a regression gate, then a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only find, or blue-team alone to only fix. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-purple-team\",\"task\":\"Install purple-team\",\"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 \"purple-team\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team. 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: Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure classes against the frozen target, blue patches the target to close them under a regression gate, then a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only find, or blue-team alone to only fix. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-purple-team\",\"task\":\"Install purple-team\",\"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 \"purple-team\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team 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: Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure classes against the frozen target, blue patches the target to close them under a regression gate, then a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only find, or blue-team alone to only fix. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-purple-team\",\"task\":\"Install purple-team\",\"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/gaasher-purple-team/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/gaasher-purple-team"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team","install":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","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","agent-skill"],"known_risks":["Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document 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":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document 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":63,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo 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","Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use purple-team in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 48/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gaasher-purple-team (purple-team)","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","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":"","skill_slug":"gaasher-purple-team","task":"Use purple-team in an agent workflow","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/gaasher-purple-team","api":"https://www.openagentskill.com/api/agent/skills/gaasher-purple-team","audit":"https://www.openagentskill.com/skills/gaasher-purple-team/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-purple-team&task=Use%20purple-team%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20purple-team%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20purple-team%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/gaasher-purple-team/install","manifest":"https://www.openagentskill.com/api/registry/manifest/gaasher-purple-team"}},"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":"github-automation","title":"GitHub automation"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":163,"starsLabel":"163","forks":19,"license":"MIT","qualityScore":63,"trustScore":75,"auditScore":76},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":67,"lastPushedAt":"2026-06-30T04:03:49+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"]},"coverageTags":["Coding","Coding agents","coding-agents","agent-skill"]},"audit":{"audit_score":76,"risk_level":"needs_review","risk_label":"Needs review","quality_score":63,"trust_score":75,"maintenance_score":88,"security_score":80,"install_score":92,"warnings":["Permission surface may require sandboxing","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"]},"quality_signals":{"model":"v2","star_score":15.5,"usage_score":0,"review_score":5.1,"metadata_score":3,"freshness_score":12},"platforms":["Claude Code"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"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"}],"stacks":[{"slug":"coding-review-agent","title":"Coding review agent","url":"https://www.openagentskill.com/collections/coding-review-agent"},{"slug":"browser-qa-agent","title":"Browser QA agent","url":"https://www.openagentskill.com/collections/browser-qa-agent"},{"slug":"research-report-agent","title":"Research report agent","url":"https://www.openagentskill.com/collections/research-report-agent"}],"install":"npx skills add gaasher/Agent-Loop-Skills --skill purple-team","install_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 gaasher-purple-team","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 \"purple-team\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team. 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: Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure classes against the frozen target, blue patches the target to close them under a regression gate, then a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only find, or blue-team alone to only fix. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-purple-team\",\"task\":\"Install purple-team\",\"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 \"purple-team\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team. 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: Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure classes against the frozen target, blue patches the target to close them under a regression gate, then a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only find, or blue-team alone to only fix. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-purple-team\",\"task\":\"Install purple-team\",\"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 \"purple-team\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team 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: Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds distinct failure classes against the frozen target, blue patches the target to close them under a regression gate, then a fresh red pass re-verifies — confirming each class is closed and surfacing any new ones the fix introduced. The find→fix→re-verify cycle repeats until a fresh attack pass stays dry (the target is hardened) or a cycle budget is hit, then it opens a pull request with the patch set. Not for attacking a system the user is not authorized to test, and not for a one-shot scan — use red-team alone to only find, or blue-team alone to only fix. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-purple-team\",\"task\":\"Install purple-team\",\"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"}],"repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team","github_repo":"gaasher/Agent-Loop-Skills","version":"1.0.0","license":"MIT","urls":{"web":"https://www.openagentskill.com/skills/gaasher-purple-team","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/purple-team","api":"/api/agent/skills/gaasher-purple-team","install_api":"/api/skills/gaasher-purple-team/install"},"meta":{"created_at":"2026-09-04T05:03:40.005111+00:00","updated_at":"2026-09-04T05:03:40.06435+00:00","agent_friendly":true}}