web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches design guidelines from Vercel Labs' official GitHub repository.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided files and external guideline content, which represents a potential attack surface.
- Ingestion points: Local files provided by the user and remote markdown guidelines from GitHub.
- Boundary markers: The instructions do not define specific delimiters to separate user data from guidelines.
- Capability inventory: The skill is limited to textual analysis and providing feedback in a specific format; no dangerous capabilities like shell execution or file writing are enabled.
- Sanitization: No explicit sanitization or filtering of the ingested content is performed.
Audit Metadata