web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches auditing rules from Vercel Labs' official GitHub repository. This source is recognized as a trusted organization, making the remote fetch safe.
  • [PROMPT_INJECTION]: The skill loads dynamic instructions from a remote Markdown file to define its auditing logic. This represents a safe implementation of indirect instruction loading since it uses a verified vendor source.
  • [COMMAND_EXECUTION]: Reads local frontend development files (React, Vue, Svelte, HTML/CSS) to perform the design audit. This file access is limited to the scope of the user's request.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 01:55 PM