web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches design guidelines from Vercel Labs' official GitHub repository. This is an expected action from a trusted source for the purpose of design review.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by fetching external instructions and applying them to local files. The risk is minimized due to the trusted nature of the source.
  • Ingestion points: SKILL.md fetches from raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md.
  • Boundary markers: No specific delimiters are used to separate guideline content from core agent instructions.
  • Capability inventory: Reading local files as specified by the user or pattern.
  • Sanitization: No explicit sanitization or validation of the fetched content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 11:12 AM
Security Audit — agent-trust-hub — web-design-guidelines