web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Downloads user interface guidelines from Vercel Labs' public repository to perform compliance checks.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external UI files provided by the user, which introduces an indirect prompt injection surface if those files contain malicious text patterns.
- Ingestion points: User-provided files or patterns specified during execution.
- Boundary markers: Absent.
- Capability inventory: None. The skill only reads files and outputs results in a terse format.
- Sanitization: Absent.
Audit Metadata