unit-test-generation
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown and YAML configuration files providing guidelines for unit test generation. No automated scripts, third-party packages, or remote downloads are present.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read existing project code and test files to inform the generation of new tests, which constitutes an ingestion point for potentially untrusted data.
- Ingestion points: Reads existing tests and local test patterns within the user's project environment (SKILL.md).
- Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" tags for the source code being analyzed.
- Capability inventory: The skill generates test files, fixtures, and commands but does not contain logic to execute them directly.
- Sanitization: There are no instructions for sanitizing or escaping the content of the files read before they are processed by the agent.
Audit Metadata