web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches design guidelines from the official Vercel Labs GitHub repository. This behavior is a legitimate operation used to retrieve the rule set for the audit task from a trusted source.
- [PROMPT_INJECTION]: Analyzed for indirect prompt injection surface. The skill ingests data from a remote URL to guide its reasoning. Evidence chain: 1) Ingestion point: fetches from GitHub in
SKILL.md. 2) Boundary markers: absent. 3) Capability: file reading. 4) Sanitization: absent. While this represents a theoretical ingestion surface, the source is a trusted repository and the behavior is central to the skill's primary function of providing design audits.
Audit Metadata