experience-search-coordinate

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows standard instructional patterns to coordinate search requests between content and media workflows. It implements human-in-the-loop confirmation steps (Step 3, point 2 and Step 4, point 2) which require users to approve search parameters before any search tool is executed.
  • [SAFE]: Data access is limited to searching Salesforce CMS metadata and content using specific MCP tools (metadata-grounding, content-readonly). The local file scanning of uiBundles/*/public/content-metadata.json is a functional requirement to resolve channel scope for the Salesforce environment.
  • [SAFE]: External dependencies are restricted to well-known Salesforce tools (MCP servers and the sf CLI). The use of mcp__skill_bridge__load_skill to invoke experience-cms-content-render is a legitimate delegation pattern within the vendor's ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 07:36 AM
Security Audit — agent-trust-hub — experience-search-coordinate