zoom-mcp/whiteboard

Pass

Audited by Gen Agent Trust Hub on May 31, 2026

Risk Level: SAFE
Full Analysis
  • Integration with Official Service Endpoints: The skill provides guidance for connecting to Zoom's official Model Context Protocol (MCP) endpoints located at mcp-us.zoom.us. Referencing well-known technology services for integration is a standard and expected functionality.
  • Authentication Best Practices: The skill recommends managing access tokens through environment variables (e.g., ZOOM_WHITEBOARD_MCP_ACCESS_TOKEN). This approach aligns with security best practices for credential management in development environments.
  • Data Interaction Surface: The skill facilitates reading content from external sources through tools like get_a_whiteboard. As with any skill that ingests external data, there is a theoretical surface for indirect prompt injection if the retrieved content contains instructions. This is a common consideration for data-processing skills, and users should ensure appropriate handling of tool outputs in downstream logic.
  • No Executable Code Detected: The skill consists entirely of instructional documentation and metadata. No scripts, binaries, or automated package installations are included, which significantly reduces the local security risk profile.
Audit Metadata
Risk Level
SAFE
Analyzed
May 31, 2026, 07:56 AM
Security Audit — agent-trust-hub — zoom-mcp/whiteboard