web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches design guidelines from Vercel Labs' official GitHub repository via https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md. This targets a well-known organization and is considered a safe operational behavior for a design review tool.
  • [PROMPT_INJECTION]: The skill processes remote content and local files, which presents a surface for indirect prompt injection.
  • Ingestion points: Fetches remote guidelines from a URL and reads local user files (SKILL.md).
  • Boundary markers: No specific delimiters are defined to separate the fetched instructions from the source code being reviewed.
  • Capability inventory: The skill utilizes network retrieval and local file reading capabilities.
  • Sanitization: There is no explicit sanitization of the guidelines or file content before processing.
  • Note: While the surface exists, the risk is mitigated by the use of a trusted source for the guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 07:53 PM
Security Audit — agent-trust-hub — web-design-guidelines