web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill uses WebFetch to retrieve instructions from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md. As vercel-labs is a Trusted GitHub Organization, this finding is downgraded to LOW.
  • PROMPT_INJECTION (LOW): The skill exhibits an Indirect Prompt Injection surface (Category 8) by treating remote web content as executable instructions for auditing local files.
  • Ingestion points: Fetches markdown instructions from an external URL and reads local user files.
  • Boundary markers: None. The skill does not define delimiters or provide 'ignore embedded instructions' warnings for the fetched content.
  • Capability inventory: The agent reads local file content and processes it based on the fetched rules.
  • Sanitization: No validation or sanitization of the remote instructions is performed before they are applied to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:37 PM