Skills
skills/sumik5/sumik-claude-plugin/using-drawio-mcp/Gen Agent Trust Hub

using-drawio-mcp

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official @drawio/mcp Node.js package and the jgraph/drawio-mcp GitHub repository. These are well-known and trusted resources managed by the official draw.io maintainers.
  • [INDIRECT_PROMPT_INJECTION]: The tools open_drawio_mermaid, open_drawio_xml, and open_drawio_csv accept a content parameter which can be a string or a URL. This represents an indirect prompt injection surface where the agent might process untrusted diagram definitions or fetch content from external URLs.
  • Ingestion points: content parameter in INSTRUCTIONS.md for all three tools.
  • Boundary markers: No specific delimiters or "ignore" instructions are provided to the agent for handling untrusted diagram content.
  • Capability inventory: The tools facilitate fetching remote data (via URL) and rendering it in a browser-based editor.
  • Sanitization: No sanitization logic is described within the skill's instruction files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 02:12 PM