generating-unit-tests
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface.
- Ingestion points: Source code files are read from the project src directory as specified in SKILL.md.
- Boundary markers: No delimiters are used to separate untrusted source content from agent instructions.
- Capability inventory: The agent can write files and execute bash commands (restricted to test:unit-*) as defined in SKILL.md.
- Sanitization: No sanitization or validation of the ingested source code is performed before it is used to generate new test files.
Audit Metadata