tdd
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external specifications to generate code and tests, creating a potential surface for indirect instruction injection.\n
- Ingestion points: The agent reads requirements, examples, and 'docs/tech-spec.md' (SKILL.md).\n
- Boundary markers: None specified.\n
- Capability inventory: Writing implementation code, writing test files, and identifying/executing shell commands.\n
- Sanitization: None specified.\n- [COMMAND_EXECUTION]: The skill instructions involve identifying and returning the project's test commands for execution.\n
- Evidence: 'Input: ... the project's test command', 'Return the red/green commands and outcomes to the calling workflow.'
Audit Metadata