web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches configuration guidelines from Vercel Labs' official GitHub repository.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided files, representing an attack surface for indirect instructions. Ingestion points: User-specified files or patterns (SKILL.md). Boundary markers: Not explicitly defined for separating file content from guidelines. Capability inventory: File reading and network fetch (SKILL.md). Sanitization: None identified in the provided instructions.
Audit Metadata