web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches design guidelines from Vercel Labs' official GitHub repository.
- [INDIRECT_PROMPT_INJECTION]: The skill processes instructions from an external source which creates an indirect prompt injection surface.
- Ingestion points: The skill fetches instructions from
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.mdas described inSKILL.md. - Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are provided in the skill instructions.
- Capability inventory: The skill reads local files based on user-provided paths or patterns for review.
- Sanitization: No sanitization or validation of the fetched content is performed; the instructions are followed directly as rules for the audit process.
- Note: The source is a well-known and trusted organization, which minimizes the associated security risk.
Audit Metadata