web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches design guidelines from the Vercel Labs GitHub repository. This is an expected behavior for retrieving the latest rules for UI review and does not pose a security risk.
  • [DATA_EXPOSURE]: The skill reads user-specified files to perform its primary function of UI review. It does not access sensitive system directories, environment variables, or hardcoded credentials.
  • [PROMPT_INJECTION]: The skill is designed to follow instructions fetched from an external source, which represents an indirect prompt injection surface. However, the source is a well-known service and the agent is instructed to use the content specifically for UI rule application.
  • [REMOTE_CODE_EXECUTION]: No patterns for remote code execution or dynamic script evaluation were detected. The external content is processed as guidelines for analysis rather than executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 01:44 PM
Security Audit — agent-trust-hub — web-design-guidelines