web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches design guidelines from Vercel Labs' official GitHub repository via WebFetch.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted user-provided UI code to perform audits.\n
  • Ingestion points: Local files or file patterns specified by the user as arguments.\n
  • Boundary markers: None; there are no specific markers or instructions to isolate user code from the agent's logic.\n
  • Capability inventory: Reading local file content and making network requests via WebFetch.\n
  • Sanitization: None; the skill does not perform validation or filtering of the content within the reviewed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 08:06 PM