web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches design guidelines from the official Vercel Labs repository on GitHub to provide rules for the UI audit.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests guidelines from a remote source and processes local code files, creating a surface for potential instruction injection.
- Ingestion points: Remote markdown files fetched from GitHub and local UI code files.
- Boundary markers: There are no explicit delimiters used to separate the fetched guidelines or local file content from the agent's system instructions.
- Capability inventory: The skill is limited to reading files and outputting review findings; it does not utilize shell execution, file modification, or network exfiltration tools.
- Sanitization: No sanitization or validation of the fetched guideline content is specified before it is applied to the review process.
Audit Metadata