web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches configuration and review instructions from the Vercel Labs official GitHub repository to perform audits.
  • [COMMAND_EXECUTION]: Reads local UI code files as specified by the user to conduct the requested design check.
  • [PROMPT_INJECTION]: The skill ingests instructions from a remote URL to define its auditing logic, representing an indirect prompt injection surface.
  • Ingestion points: Remote content fetched from the Vercel Labs repository via SKILL.md.
  • Boundary markers: Absent for the fetched remote guidelines.
  • Capability inventory: Read access to local project files.
  • Sanitization: No explicit validation or filtering of the fetched content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 01:24 AM