test-driven-development
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION] (SAFE): The skill uses authoritative language such as 'MANDATORY', 'The Iron Law', and 'Delete it. Start over.' These are intended to enforce the TDD methodology and do not attempt to bypass core AI safety filters or extract system prompts.
- [COMMAND_EXECUTION] (SAFE): The documentation references standard local development commands like 'npm test'. There are no instances of arbitrary command execution or suspicious shell piping.
- [DATA_EXPOSURE] (SAFE): No hardcoded credentials, sensitive file paths, or external network requests were identified in the markdown or code examples.
- [INDIRECT_PROMPT_INJECTION] (LOW): While the skill instructs the agent to delete code written without tests, this is a procedural guideline for the TDD workflow rather than a malicious injection. It operates on the local environment where the agent has existing coding capabilities.
Audit Metadata