tdd-spec
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill is purely instructional and contains no code or external dependencies.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (project issues and requests), which is an inherent surface for indirect prompt injection. This is considered safe given the skill's specific use case and lack of dangerous capabilities.\n
- Ingestion points: Processes external request and issue descriptions (SKILL.md, Step 1).\n
- Boundary markers: Absent.\n
- Capability inventory: File system write access is used to save documentation; no network or code execution tools are utilized (SKILL.md, Step 7).\n
- Sanitization: The skill instructs the user to use filesystem-safe titles for generated files.
Audit Metadata