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 fetches a markdown file from 'https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md'. Since 'vercel-labs' is a trusted GitHub organization, the download itself is considered low risk.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) because it retrieves instructions ('rules') from an external source and applies them to local files.
  • Category 8 Evidence Chain:
  • Ingestion points: Fetching 'command.md' via WebFetch and reading local files provided by the user.
  • Boundary markers: None specified in the instructions to separate fetched rules from system instructions.
  • Capability inventory: The skill uses WebFetch for network access and reads local files.
  • Sanitization: No sanitization or validation of the fetched markdown instructions is performed before application.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:23 PM