dat-docs-mcp
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches live documentation and API reference data from official Meta developer domains (developer.meta.com and wearables.developer.meta.com).
- [COMMAND_EXECUTION]: Includes instructions for the user to run the official Model Context Protocol inspector utility using npx to verify connection to the server.
- [INDIRECT_PROMPT_INJECTION]: The skill provides the search_dat_docs tool which ingests content from an external documentation server, representing a potential surface for indirect injection.
- Ingestion points: Content retrieved via the search_dat_docs tool from https://mcp.developer.meta.com/wearables.
- Boundary markers: Absent; no specific instructions are provided to the agent for delimiting or sanitizing documentation results.
- Capability inventory: Performs semantic search over guides, API symbols, and code examples to provide technical context.
- Sanitization: Absent; the skill relies on the agent's internal safety guardrails when processing documentation content.
Audit Metadata