mermaid-diagrams

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the Mermaid CLI tool from the well-known @mermaid-js organization on NPM. It also references a community-maintained Docker image (minlag/mermaid-cli) for containerized rendering.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute mmdc (Mermaid CLI) for converting diagram definitions into image formats. It includes guidance on configuring Puppeteer for restricted environments.
  • [PROMPT_INJECTION]: The skill processes text-based diagram definitions, which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: Processes diagram definitions from .mmd files or standard input.
  • Boundary markers: Not explicitly defined; input is passed directly to the rendering tool.
  • Capability inventory: Utilizes the Bash tool to run the rendering engine and Write to save resulting files.
  • Sanitization: Relies on the default sanitization provided by the Mermaid engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 03:59 AM
Security Audit — agent-trust-hub — mermaid-diagrams