test-pruner
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read and process external, potentially untrusted content such as AGENTS.md, CONTRIBUTING files, and the project's source code and test files.
- Ingestion points: AGENTS.md, CONTRIBUTING, production source code, and test files.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions in external data are provided.
- Capability inventory: The skill implies capabilities to read, edit, and delete files within the project directory to perform test pruning.
- Sanitization: There is no mention of sanitizing or escaping the content read from these external files before processing.
Audit Metadata