agent-readable-code
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of a static analysis linter and documentation designed to help developers write code that is more easily understood by AI agents. The linter script (scripts/lint.py) is written in Python using only standard library modules and performs no network communication or data exfiltration.\n- [SAFE]: Heuristic detections of dangerous functions such as eval() and subprocess.run() are isolated to the test suite and fixture files, which are used to verify the linter's functionality and are not part of the active skill logic.\n- [SAFE]: No prompt injection or behavior-override patterns were found in the documentation or markdown instructions. All recommendations are focused on code structure and maintainability.
Audit Metadata