pytest-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a set of instructional markdown documents designed to help agents or users follow best practices for pytest. No malicious instructions, obfuscation, or unauthorized access patterns were found during the analysis.
- [NO_CODE]: The skill contains no executable code, binary files, or script configurations. It does not initiate any subprocesses or dynamic code execution.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external code files for review, which creates an inherent surface for indirect prompt injection. However, the risk is mitigated by the skill's complete lack of dangerous capabilities such as file writing, network operations, or command execution.
- Ingestion points: Local Python source files and test configuration files (e.g., test_*.py, conftest.py) read by the agent.
- Boundary markers: The skill provides instructions for scoping the review but lacks explicit technical delimiters to separate untrusted code from instructions.
- Capability inventory: No tools or capabilities are defined within the skill that could be exploited by an injection attack.
- Sanitization: The skill performs no execution or transformation of data, requiring no sanitization beyond standard agent guardrails.
Audit Metadata