web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill fetches guidelines from
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md. This is a remote download of instructions. Since 'vercel-labs' is a trusted GitHub organization, the severity is downgraded per [TRUST-SCOPE-RULE]. - PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it fetches and executes instructions from a remote source.
- Ingestion points: Remote Markdown file (
command.md). - Boundary markers: Absent; the agent is instructed to directly 'Fetch fresh guidelines before each review' and 'Apply all rules'.
- Capability inventory: File system read access (via user-provided files/patterns).
- Sanitization: None; the agent consumes the remote instructions as authoritative.
Audit Metadata