web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches updated UI guidelines from Vercel Labs' official GitHub repository.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and follows instructions from an external source.
  • Ingestion points: UI guidelines are fetched from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md during execution.
  • Boundary markers: There are no explicit markers or 'ignore embedded instructions' warnings for the fetched content.
  • Capability inventory: The skill uses file system read and WebFetch capabilities.
  • Sanitization: No sanitization or validation of the fetched rules is performed before the agent processes them.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:11 AM
Security Audit — agent-trust-hub — web-design-guidelines