hai-tdd
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run test commands at various stages (RED, GREEN, and REFACTOR) to verify implementation. This is the primary and intended function of the skill to facilitate a test-driven development workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill takes user input regarding feature implementations or bug fixes to drive the development loop. The risk of malicious instructions in this data is mitigated by the skill's strict requirement for verifiable evidence (test results and observed failures) at every step, as outlined in the provided output template.
Audit Metadata