Skills
skills/thomast1906/github-copilot-agent-skills/drawio-mcp-diagramming/Gen Agent Trust Hub

drawio-mcp-diagramming

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill contains utility scripts (search_aws4_icons_github.py and search_azure2_icons_github.py) designed to retrieve icon metadata and stencil definitions from the official jgraph/drawio GitHub repository. These scripts target well-known, trusted domains for administrative maintenance and do not involve executing untrusted remote code.
  • [SAFE]: The skill exhibits no signs of prompt injection, data exfiltration, or obfuscation. It functions as a specialized diagramming guide, utilizing local static catalogs for runtime operations and an official Draw.io MCP endpoint.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 10:17 AM
Security Audit — agent-trust-hub — drawio-mcp-diagramming