web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches audit rules and formatting guidelines from the official Vercel Labs GitHub repository.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing untrusted user files alongside external instructions.
  • Ingestion points: Local source files identified by file-or-pattern and the guidelines source URL.
  • Boundary markers: None specified in the instructions.
  • Capability inventory: Local file system access and network operations via WebFetch.
  • Sanitization: No explicit validation or filtering of input file contents.
  • [SAFE]: All external resources are retrieved from trusted vendors, and the skill's activities are strictly limited to its stated purpose of UI code auditing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 03:36 PM