claude-md-generator Audit report.

Warnings

• Dependency or permission surface needs review
• Permission surface may require sandboxing
• Inconsistency in line count target: SKILL.md says 'under 100 lines' but evals expect 'under 200 lines'.
• Evals mention 'Calls Gemini with analysis' which is not referenced in SKILL.md; may be a leftover from a different version.
• Uses `python3` which may not be available on all systems; could fallback to other JSON parsers.
• Quality score needs review
• Permission surface needs review: secrets or environment access, shell or command execution
• Dependency/runtime risk: command execution surface, credential or environment access
• Permission surface: secrets or environment access, shell or command execution

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.