web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches configuration and guidelines from Vercel Labs' official GitHub repository.
  • [PROMPT_INJECTION]: The skill processes instructions from a remote URL, creating a surface for indirect prompt injection.
  • Ingestion points: Fetches content from a remote GitHub URL specified in SKILL.md.
  • Boundary markers: No explicit delimiters are present to isolate fetched instructions.
  • Capability inventory: The skill is designed to read local files specified by the user.
  • Sanitization: No validation or sanitization is performed on the fetched content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 11:35 AM
Security Audit — agent-trust-hub — web-design-guidelines