doc-it
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted source code and existing documentation to generate new content, creating a surface for indirect prompt injection. \n- Ingestion points: The agent reads canonical source files and documentation within the .docs/ directory. \n- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the ingested content. \n- Capability inventory: The skill is restricted to reading local files and writing markdown documentation. It does not possess network access, shell execution, or dynamic code evaluation capabilities. \n- Sanitization: The skill includes explicit hygiene instructions to prevent the inclusion of secrets, tokens, PII, or internal IDs in the generated documentation.
Audit Metadata