docs
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains comprehensive instructions for maintaining software documentation and code comments. It promotes industry-standard practices and emphasizes the importance of factual verification against the source code.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it reads source code, tests, and existing documentation to inform its output. It encourages the use of boundary markers by instructing the agent to separate plans from facts and to label different content types. The capability inventory includes file access and potential command execution for verifying documentation examples. Mitigation is provided through explicit instructions to exclude secrets and private data from any documentation generated.
Audit Metadata