web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches fresh guidelines from Vercel Labs' official GitHub repository (raw.githubusercontent.com/vercel-labs/web-interface-guidelines). This is a documented and standard practice for keeping design rules up to date from a trusted source.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a remote URL to guide its review process. While this technically introduces a remote ingestion surface, the source is a well-known service and the risk is mitigated by the trusted nature of the provider.
  • Ingestion points: SKILL.md fetches guidelines from a GitHub raw URL.
  • Boundary markers: None explicitly defined in the fetch command, but instructions are scoped to design review.
  • Capability inventory: Uses WebFetch for network reads and file reading for UI code review; no file-write or subprocess execution capabilities are present.
  • Sanitization: Standard LLM processing of text content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:31 PM
Security Audit — agent-trust-hub — web-design-guidelines