tdd
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides educational content regarding the red-green-refactor loop and effective testing strategies. No suspicious commands, scripts, or persistence mechanisms are present in the provided files.
- [INDIRECT_PROMPT_INJECTION]: The skill involves the processing of external project files, which is an inherent surface for indirect prompt injection.
- Ingestion points: Instructions in SKILL.md direct the agent to read GLOSSARY.md and codebase source files to align test vocabulary with project domain language.
- Boundary markers: The skill does not provide specific delimiters or warnings to ignore instructions embedded in the project files.
- Capability inventory: The skill is intended to assist in code generation and bug fixes, utilizing the agent's internal file and terminal tools.
- Sanitization: No specific sanitization measures for external codebase content are mentioned.
Audit Metadata