tdd-test-writer
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No override instructions, safety bypass markers, or malicious redirection patterns were found in the skill text.
- [DATA_EXPOSURE_AND_EXFILTRATION]: Analysis did not detect hardcoded credentials, access to sensitive file paths, or unauthorized data exfiltration patterns.
- [DYNAMIC_EXECUTION]: The skill instructs the agent to generate and execute test code locally through standard frameworks (e.g., jest, pytest), which is the intended primary purpose and poses no inherent security risk.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect injection as it processes user requirements to generate code.
- Ingestion points: User requests and repository code (SKILL.md).
- Boundary markers: None defined.
- Capability inventory: Subprocess execution for test runners (SKILL.md).
- Sanitization: No explicit sanitization or validation of user input is described.
Audit Metadata