web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches design guidelines from Vercel Labs' public GitHub repository (raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md). This targets a well-known service and a trusted organization.
  • [DATA_EXPOSURE]: Reads local project files provided by the user to perform the UI audit. This file access is limited to the scope of the review requested by the user and is consistent with the skill's stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests instructions from a remote Markdown file.
  • Ingestion points: Fetches guidelines from an external URL in SKILL.md.
  • Boundary markers: None explicitly defined for the fetched content.
  • Capability inventory: Reads local files and performs web fetches.
  • Sanitization: Not explicitly implemented.
  • Note: While fetching remote instructions is a known attack surface, the source (Vercel Labs) is a trusted organization, mitigating the risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 07:51 AM