web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches design guidelines from Vercel Labs' official GitHub repository. This external content is used to define the rules and format for the UI audit.
- [PROMPT_INJECTION]: The skill processes untrusted user-provided source code files to perform UI reviews. This creates a surface for indirect prompt injection where malicious instructions embedded in the code being audited (e.g., in HTML/code comments) could attempt to influence the agent's behavior.
- Ingestion points: The skill reads files or file patterns specified by the user as seen in the 'How It Works' section of SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the ingested file content.
- Capability inventory: Performs file read operations and network requests to a trusted source.
- Sanitization: No explicit sanitization or filtering of the file content is mentioned prior to processing.
Audit Metadata