docs-author
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a structured methodology for generating technical documentation and contains no suspicious code or instructions.\n- [COMMAND_EXECUTION]: The skill executes a local Python script (
scripts/docs_lint.py) to perform static analysis on the documentation tree. The script uses only standard library modules and performs regex-based checks for internal consistency without network or sensitive file access.\n- [INDIRECT_PROMPT_INJECTION]:\n - Ingestion points: The skill reads repository content including
README.md, existing documentation files, and issue tracker content to inform the writing process.\n - Boundary markers: None explicitly defined in the instructions, though the agent's behavior is guided by a strict mode-based classification system.\n
- Capability inventory: The skill can write files to the
docs/directory and execute a local linter script.\n - Sanitization: Untrusted data from repository files is not explicitly sanitized, but it is processed as documentation content rather than instructions.
Audit Metadata