py-anti-patterns
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill contains static documentation and code review rules focused on Python best practices. There are no command execution patterns, network operations, or external dependencies requested in the file.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external code as part of its primary function. While this creates a potential attack surface, the risk is mitigated by a lack of dangerous capabilities (such as file writing or network access) and the inclusion of specific safety instructions.
- Ingestion points: External code snippets and tool outputs provided to the agent for review as described in the 'Applies when' sections of the rules.
- Boundary markers: The 'Sensitive Evidence Safety' section serves as a boundary instruction, directing the agent on how to handle untrusted or sensitive content.
- Capability inventory: No subprocess calls, network operations, or file-system writing capabilities are defined in this skill.
- Sanitization: The skill explicitly instructs the agent not to quote or reproduce sensitive values (credentials, keys, etc.) discovered during reviews, directing it to report only existence and location.
Audit Metadata