web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches fresh UI guidelines from the Vercel Labs official GitHub repository before performing a review.
  • [PROMPT_INJECTION]: The skill processes instructions from an external source and user-provided files, which represents an indirect prompt injection surface.
  • Ingestion points: External guidelines file (command.md) and user-specified code files.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: File system read access and network fetching capabilities.
  • Sanitization: Relies on the underlying model to interpret the fetched markdown instructions safely.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 05:32 AM
Security Audit — agent-trust-hub — web-design-guidelines