documentation
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill focuses on generating documentation by inspecting local repository files to ensure accuracy. It strictly prohibits the fabrication of facts, commands, or features, requiring all documentation to be grounded in verifiable repository evidence.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository it documents. (1) Ingestion points: Entire repository content including source code, manifests, and existing documentation. (2) Boundary markers: None specified for the ingested content. (3) Capability inventory: Local file reading and execution of the bundled generate_tree.py script. (4) Sanitization: None specified; however, instructions mandate factual verification and omit claims with weak evidence.
Audit Metadata