create-workflow-diagram

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a Node.js script, screenshot-diagram.js, which uses a headless browser to automate the creation of PNG files from generated HTML.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the playwright library and the Chromium browser via npm and npx to support its image generation features.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because it interpolates user-provided workflow labels and descriptions directly into HTML templates without evidence of sanitization.
  • Ingestion points: User-provided workflow steps, tool names, and icons collected during Phase 1.
  • Boundary markers: The skill does not employ delimiters or specific instructions to prevent embedded commands in the user input from affecting the HTML structure.
  • Capability inventory: The skill can perform file system writes and execute a local Node.js script for screenshotting.
  • Sanitization: No HTML escaping or validation logic is specified for the text parsed from user input before it is rendered.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:06 PM
Security Audit — agent-trust-hub — create-workflow-diagram