uiuxdesign
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches design and interface guidelines from Vercel Labs' official GitHub repository (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md). This external reference is used to ensure that the generated UI follows best practices established by the industry.
- [INDIRECT_PROMPT_INJECTION]: The skill implements a process for reviewing UI against external guidelines, which involves ingesting remote content. * Ingestion points: Markdown files containing guidelines are fetched from a remote GitHub repository at runtime. * Boundary markers: The skill does not explicitly define delimiters to separate fetched instructions from the main prompt context. * Capability inventory: The agent has the capability to write and modify source code, execute shell commands for package management, and run automated browser tests via Playwright. * Sanitization: The skill does not describe specific sanitization or filtering logic for the content retrieved from the remote URL.
- [COMMAND_EXECUTION]: The documentation provides instructions for standard development operations using npm, npx, vitest, and playwright. These commands are standard for the frontend development and testing workflows described in the skill.
Audit Metadata