web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches guidelines from Vercel Labs' official GitHub repository at raw.githubusercontent.com/vercel-labs/web-interface-guidelines.
- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by fetching external instructions that dictate the agent's auditing logic.
- Ingestion points: SKILL.md (retrieves command.md from GitHub).
- Boundary markers: None identified in the prompt configuration to separate external rules from system instructions.
- Capability inventory: File reading and UI analysis.
- Sanitization: The skill does not implement specific sanitization or validation of the fetched design rules before execution.
Audit Metadata