search-docs
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill interacts exclusively with official vendor infrastructure at mcp.facebook.com and uses approved vendor tools for discovery and usage tracking.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external documentation search results which could theoretically contain instructions. Ingestion points: Results from devtools_discovery in SKILL.md. Boundary markers: Absent. Capability inventory: Restricted to search and telemetry tools; no access to shell, file system, or sensitive user data. Sanitization: Not specified.
Audit Metadata