py-async-patterns
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill content is purely instructional, defining patterns for Python asynchronous code review. It does not contain any executable scripts, remote downloads, or malicious logic.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external code and tool outputs, which represents an ingestion surface. 1. Ingestion points: Changed code and tool output context. 2. Boundary markers: The skill includes a 'Sensitive Evidence Safety' section to guide the agent in handling secrets found in code, though explicit delimiters for the code itself are not defined. 3. Capability inventory: References the use of code analysis tools like ruff, pyright, and mypy. 4. Sanitization: No specific input sanitization is mentioned, but the skill advises against reproducing sensitive values in outputs.\n- [SAFE]: The skill references official documentation at docs.python.org, which is a well-known and trusted service.
Audit Metadata