web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the latest Web Interface Guidelines from Vercel Labs' official GitHub repository (vercel-labs/web-interface-guidelines). This is a routine operation to ensure the audit uses current standards from a trusted provider.
- [PROMPT_INJECTION]: The skill processes untrusted data from user-specified files to perform its UI review. This creates a surface for indirect prompt injection where malicious content in the audited files could attempt to influence the agent's behavior.
- Ingestion points: Local files identified by the user-provided file path or pattern in
SKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" markers are defined to isolate the content of the files being reviewed.
- Capability inventory: Reading local files and fetching content via WebFetch.
- Sanitization: The skill does not implement explicit sanitization or filtering for the content within the reviewed files.
Audit Metadata