skills/pavelsimo/skills/mermaid/Gen Agent Trust Hub

mermaid

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to use npx to fetch and run the official Mermaid CLI package (@mermaid-js/mermaid-cli) for syntax validation purposes.
  • [COMMAND_EXECUTION]: The skill executes the mmdc command (Mermaid CLI) within a temporary directory to verify the validity of generated diagram syntax.
  • [PROMPT_INJECTION]: The skill processes potentially untrusted data from source files and user descriptions to generate its output.
  • Ingestion points: Analyzes file contents from paths, directory globs, or direct text descriptions provided via the command arguments.
  • Boundary markers: The instructions do not specify explicit delimiters for untrusted input data, but the agent is tasked with structural extraction rather than direct obedience.
  • Capability inventory: The agent can write files to the filesystem (guarded by a mandatory confirmation prompt) and execute the Mermaid CLI tool.
  • Sanitization: Input content is not explicitly sanitized before analysis, relying on the structural extraction process to ignore malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 04:14 PM
Security Audit — agent-trust-hub — mermaid