code-review-python
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a defensive reference guide that lists common security pitfalls in Python code for the purpose of auditing. It does not include any executable code, network operations, or persistence mechanisms.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as its primary function is to ingest and analyze untrusted external data (Python source code from repositories or pull requests).
- Ingestion points: Reads Python source code from external repositories, pull requests, or services as specified in the 'When it applies' section.
- Boundary markers: The instructions do not explicitly provide boundary markers or delimiters to isolate untrusted code from the agent's instructions.
- Capability inventory: The skill utilizes local analysis tools including
ripgrep,bandit, andsemgrepto process the data. - Sanitization: There is no explicit mention of sanitizing or escaping the content of the files being reviewed.
- Context: This risk is inherent to the intended primary purpose of the skill (code review). The analysis suggests this is a low-risk surface given the context of a manual-style reference.
Audit Metadata