qa-pytest-writer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from untrusted external sources to generate executable Python code.
- Ingestion points: Test case specifications, requirements, and manual test designs provided in the context or source documents.
- Boundary markers: No delimiters or instructions are provided to the agent to ignore potentially malicious instructions embedded within the test specifications.
- Capability inventory: The skill workflow involves writing Python (.py) files to the tests/unit directory.
- Sanitization: There is no evidence of sanitization or validation logic to prevent a malicious test step (e.g., instructions to delete directories) from being translated into destructive code.
Audit Metadata