drawio-architecture

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The analyzed skill collection consists of legitimate developer tools and instructional content. The instructions are transparent, follow established engineering patterns, and do not exhibit malicious intent.
  • [COMMAND_EXECUTION]: The repository contains scripts such as setup_drawio_mcp.py and download-issues.sh. These are used appropriately to configure local IDE settings and interface with external APIs like SonarQube. The execution logic is clear and pertains directly to the skill's stated purpose.
  • [CREDENTIALS_UNSAFE]: The skill integrates with SonarQube using environment variables for authentication. It demonstrates good security practice by explicitly instructing the agent not to print, log, or expose these sensitive tokens.
  • [EXTERNAL_DOWNLOADS]: The skill references and installs well-known, official packages such as the @drawio/mcp server and the @modelcontextprotocol/sdk. These dependencies originate from trusted sources within the software development community.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 09:12 PM
Security Audit — agent-trust-hub — drawio-architecture