tdd-workflow
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill generates Python code files and executes them via the Bash tool using commands like 'poetry run pytest'. This dynamic execution is essential for the TDD workflow but constitutes a capability for running newly created content.
- [PROMPT_INJECTION]: Detected an indirect prompt injection surface. The skill interpolates user-provided feature descriptions directly into subagent tasks in Phase 1 and Phase 2 without sanitization or boundary markers. Ingestion points: user-provided feature descriptions in SKILL.md. Boundary markers: absent. Capability inventory: Bash and Task tool for subagent execution. Sanitization: absent.
Audit Metadata