python-docstrings
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
subprocess.runinscripts/verify_doc_only_diff.pyto callgitfor diffing and repository root detection. It also providesscripts/smoke_test.shfor local verification. These executions are scoped to local repository management and do not use shell interpolation, following secure implementation practices. - [INDIRECT_PROMPT_INJECTION]: The skill processes Python files and docstrings from the local environment. It manages the risk of accidental logic changes or instruction following by providing a verification tool that compares the AST of the code before and after documentation changes, ensuring semantic consistency.
- [SAFE]: All included scripts use standard Python library modules (like
astandtokenize) and do not perform network requests, access sensitive system files (e.g., SSH keys, credentials), or employ obfuscation techniques.
Audit Metadata