web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches guidelines from Vercel Labs' official GitHub repository, which is a trusted source.
  • [PROMPT_INJECTION]: The skill is designed to ingest and follow instructions from an external markdown file, creating an indirect prompt injection surface.
  • Ingestion points: Guidelines fetched from the Vercel Labs repository in SKILL.md.
  • Boundary markers: None specified to isolate remote instructions.
  • Capability inventory: Includes local file reading and network fetching.
  • Sanitization: No explicit validation of the fetched content. This implementation is considered safe as it utilizes a trusted organization for its remote instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 12:17 PM