test-first-mentor
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely conversational and focuses on mentoring the user in test-driven development (TDD) practices. It does not include any executable code, scripts, or external dependencies.
- [SAFE]: No sensitive data access or network operations are present. The use of
SKILL_MEMORY.mdfor state persistence is a standard design pattern for agent skills to track workflow progress and does not pose a security risk in this context. - [SAFE]: The skill's instructions focus on restricting the AI agent's behavior (e.g., refusing to discuss implementation details) to achieve its educational goal, which aligns with safe and intended operational boundaries.
Audit Metadata