web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches rules and UI guidelines from Vercel Labs' official GitHub repository. This is a trusted source and the action is central to the skill's purpose.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the analysis of external content and user-provided code.
  • Ingestion points: Processes local file content and remote guidelines from a URL.
  • Boundary markers: No delimiters or instructions are used to separate audited data from the agent's core instructions.
  • Capability inventory: Can read local files and make network requests using the WebFetch tool.
  • Sanitization: Lacks sanitization or validation of the processed input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 09:49 AM