web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches fresh guidelines from Vercel Labs' official GitHub repository (github.com/vercel-labs). This represents standard functionality for retrieving updated design rules from a trusted source.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process external text which is then used as instructions to evaluate local code. While this creates a theoretical injection surface, the use of a trusted source for the guidelines minimizes this risk.
  • Ingestion points: The command.md file fetched from the remote source URL.
  • Boundary markers: None identified in the skill instructions.
  • Capability inventory: The agent is permitted to read local files and use WebFetch to retrieve the guidelines.
  • Sanitization: No explicit sanitization or escaping of the fetched guideline content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:19 AM
Security Audit — agent-trust-hub — web-design-guidelines