web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches design guidelines from Vercel Labs' official GitHub repository (vercel-labs/web-interface-guidelines). This is a trusted source.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it follows instructions found in the remotely fetched guidelines.
  • Ingestion points: Remote markdown file fetched from GitHub (SKILL.md).
  • Boundary markers: Absent; the agent is instructed to fetch and apply all rules from the external file directly.
  • Capability inventory: Reads local files and performs web fetching.
  • Sanitization: Absent; external content is interpolated directly into the task instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 12:09 PM
Security Audit — agent-trust-hub — web-design-guidelines