mermaid

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses a setup script (scripts/ensure-deps.sh) to install the beautiful-mermaid library from the official NPM registry.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to locate its internal directory and execute Node.js scripts (extract_mermaid.js, render.js, resilient_diagram.js) for diagram processing and validation.
  • [INDIRECT_PROMPT_INJECTION]: The 'Code-to-Diagram' feature involves analyzing untrusted local source code. Ingestion points: Local project files and configuration files. Boundary markers: Absent. Capability inventory: Read, Bash, Write, Edit. Sanitization: Not explicitly defined in the scripts for the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 12:28 PM
Security Audit — agent-trust-hub — mermaid