test-driven-development
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- General (SAFE): The skill content is strictly educational and methodological, focusing on the Red-Green-Refactor cycle and test quality.
- Prompt Injection (SAFE): Although the skill uses strong imperative language like 'The Iron Law' and 'Delete means delete', these instructions are contextually bound to software engineering discipline and do not attempt to override the agent's safety filters or extract system prompts.
- Command Execution (LOW): The skill references 'npm test', which is a standard and expected command for a TDD-focused skill. No arbitrary or malicious execution patterns were found.
- Data Exposure (SAFE): No access to sensitive file paths (~/.ssh, .env) or hardcoded credentials was detected.
- External Downloads (SAFE): No remote scripts or unverifiable packages are downloaded or executed.
Audit Metadata