web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches configuration and design guidelines from Vercel Labs' public GitHub repository.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests instructions from a remote source to determine its review logic and output format, which introduces a potential surface for indirect instruction injection.
- Ingestion points: Remote markdown file fetched via URL (SKILL.md)
- Boundary markers: Absent in the skill instructions
- Capability inventory: File system read access, network retrieval
- Sanitization: None specified for the fetched content
Audit Metadata