wds-7-design-system

Warn

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill dynamically generates a single-page exploration application and an interactive HTML catalog based on design system data and project specifications.
  • [COMMAND_EXECUTION]: The skill initiates a localhost web server to host and serve the generated component browser and preview tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes an import feature that processes data from external URLs and Figma projects to create design system components, representing an attack surface for indirect prompt injection. Ingestion points: workflow-import.md and workflow-edit.md. Boundary markers: Absent. Capability inventory: Writing files and starting a localhost web server. Sanitization: Absent.
  • [EXTERNAL_DOWNLOADS]: The generated HTML catalog references CSS and font assets from well-known services, specifically Tailwind CSS and Google Fonts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 16, 2026, 02:12 AM