agents-md
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were identified. The skill's instructions are purely focused on improving project documentation and agent context management.
- [SAFE]: The skill implements an 'Interactive Intake' workflow that requires user interaction and codebase investigation, which is standard behavior for development-oriented agent skills.
- [SAFE]: References to external tools like linters and test runners are used for code quality and verification as part of the intended project management purpose.
- [SAFE]: The skill provides guidance on avoiding 'anti-patterns' such as command dumps or deep directory trees, which actually helps reduce the risk of the agent becoming confused by irrelevant or excessive information.
Audit Metadata