moai-docs-validation
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted documentation data, creating an indirect prompt injection surface (Category 8).\n
- Ingestion points: Reads local markdown documentation files and retrieves remote library documentation via the Context7 MCP.\n
- Boundary markers: The skill does not define explicit delimiters or instructions to prevent the agent from executing instructions potentially embedded in the validated text.\n
- Capability inventory: The agent has access to file system read tools (Read, Glob, Grep) and network tools (WebFetch, WebSearch).\n
- Sanitization: No explicit sanitization of content is described beyond structural and syntax validation.\n- [COMMAND_EXECUTION]: The skill describes the use of local Python scripts for automated validation tasks (e.g.,
python3 .moai/scripts/validate_docs.py). While typical for CI/CD workflows, this represents command execution within the agent's environment.\n- [EXTERNAL_DOWNLOADS]: The skill usesWebFetchandWebSearchto access remote data. It also references official documentation sources like Wikipedia and themoai-adkrepository on GitHub.
Audit Metadata