web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches configuration and review rules from Vercel Labs' official GitHub repository at 'https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md'. This is a trusted source for design audit criteria.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by fetching behavioral instructions from an external source.
  • Ingestion points: SKILL.md (guidelines fetch step)
  • Boundary markers: Absent
  • Capability inventory: Network fetch, local file read
  • Sanitization: Absent
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill's behavior is consistent with its stated purpose of auditing UI code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:23 AM
Security Audit — agent-trust-hub — web-design-guidelines