web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves design guidelines from Vercel Labs' official GitHub repository (vercel-labs/web-interface-guidelines). This is a well-known service and a trusted source.
  • [PROMPT_INJECTION]: The skill processes external data (user-provided files) which presents a surface for indirect prompt injection.
  • Ingestion points: Reads files matching user-provided patterns and content from a remote URL.
  • Boundary markers: None explicitly defined for user file content.
  • Capability inventory: Limited to fetching a URL and reading local files; no file writing, shell execution, or external network posts are performed.
  • Sanitization: No explicit sanitization of input files is mentioned, but the risk is mitigated by the restricted capabilities of the skill and the use of a trusted guideline source.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 11:41 AM