test-driven-development
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional content and best practices for software development. It does not contain any malicious code, obfuscation, or unauthorized access patterns.
- [COMMAND_EXECUTION]: The skill instructs the agent to run standard testing commands such as
npm test. This is within the expected scope of a development-oriented skill and does not pose a security risk in this context. - [PROMPT_INJECTION]: The skill uses prescriptive language to enforce the TDD workflow (e.g., 'The Iron Law'). These instructions are legitimate methodological constraints and do not attempt to bypass the underlying AI safety protocols or perform prompt injection.
Audit Metadata