diagram-generator

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute several shell commands to gather project context, such as ls -la, find (to identify source files), and cat package.json piped to a python3 script to extract dependencies. These operations are restricted to gathering metadata for diagram generation.
  • [EXTERNAL_DOWNLOADS]: The generated SVG templates include a CSS @import statement targeting fonts.googleapis.com to load the 'JetBrains Mono' font. This is a reference to a well-known, trusted service for web assets.
  • [DATA_EXPOSURE]: The skill reads project metadata (file names and dependency lists) to understand the system architecture. This information is used within the session to generate the diagram and is not transmitted to unauthorized external endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:11 PM
Security Audit — agent-trust-hub — diagram-generator