web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches guidelines and analysis rules from Vercel Labs' official GitHub repository. This is an expected function for retrieving the latest standards and targets a trusted source.
  • [PROMPT_INJECTION]: The skill processes instructions from an external source, creating a surface for indirect prompt injection.
  • Ingestion points: Guidelines are fetched from an external Markdown file URL specified in SKILL.md.
  • Boundary markers: None; the instructions do not include markers to delimit the fetched content or warn against embedded commands.
  • Capability inventory: The skill is designed to read user-specified files and generate analysis output.
  • Sanitization: None; the integrity of the process relies on the trusted nature of the Vercel Labs repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:30 AM