py-refactor
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a guide for Python developers to improve code quality, performance, and architecture. It utilizes standard open-source tools for linting, profiling, and testing.
- [COMMAND_EXECUTION]: The skill includes shell commands for architectural enforcement (grep), performance profiling (py-spy, cProfile), and static analysis (mypy, vulture, ruff). These are standard development practices, and the commands provided use hardcoded patterns or local process IDs.
- [INDIRECT_PROMPT_INJECTION]: As a tool designed to process and refactor source code, the agent is exposed to the contents of external files. However, the skill explicitly mandates characterization tests and verification steps which serve as manual checkpoints against unintended behavior changes.
- [REMOTE_CODE_EXECUTION]: No suspicious remote code execution patterns were detected. The skill uses 'uvx' to run standard Python tools (vulture), which is a common practice in modern Python environments.
Audit Metadata