agenthub Eval
=============

Status: review
Score: 78/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Test manually in an isolated workspace and compare against safer alternatives.

Install:
npx skills add alirezarezvani/claude-skills --skill agenthub

Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- PASS Install path: Install handoff is available.
- PASS Install command safety: standard package or runtime install path
- WARN Trust score: Good trust signals with a few areas worth checking before rollout.
- WARN Audit score: Needs review
- WARN Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- PASS License clarity: MIT
- WARN 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.
- Permission surface: shell or command execution, filesystem or document access
- High-risk permission hints: Shell or command execution
- No explicit sandboxing or security restrictions are described for the spawned subagents—they execute commands in worktrees, which could be risky if not scoped carefully.
- The SKILL.md references external scripts (e.g., `dag_analyzer.py`, `references/agent-templates.md`) that are not provided in this excerpt; their safety and correctness cannot be verified from this submission alone.
- No guidance is given on limiting resource usage (e.g., maximum number of agents) or handling malicious task inputs that could lead to unintended actions.
- Quality score needs review

Validation plan:
1. Inspect repository, README/SKILL.md, license, and recent commits before production use.
2. Install in an isolated workspace or sandbox with no production secrets available.
3. Run the smallest representative task and record files touched, commands run, network access, and outputs.
4. Compare the selected skill against at least one alternative when the eval status is review or failed.
5. Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when:
- teams that need a vendor-supported SLA
- production agents without a repository review
- No explicit sandboxing or security restrictions are described for the spawned subagents—they execute commands in worktrees, which could be risky if not scoped carefully.
- High-risk permission hints: Shell or command execution
- The SKILL.md references external scripts (e.g., `dag_analyzer.py`, `references/agent-templates.md`) that are not provided in this excerpt; their safety and correctness cannot be verified from this submission alone.
- No guidance is given on limiting resource usage (e.g., maximum number of agents) or handling malicious task inputs that could lead to unintended actions.
- Quality score needs review
- Production credentials, payments, or irreversible account changes without explicit human review

URLs:
- Skill: https://www.openagentskill.com/skills/alirezarezvani-agenthub
- Audit: https://www.openagentskill.com/skills/alirezarezvani-agenthub/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=alirezarezvani-agenthub