web-design-guidelines
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches live rules from a public GitHub raw URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md), which is user-editable, third-party content that the agent reads and applies as part of its workflow, exposing it to indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill fetches runtime rules that directly control the agent's checking behavior from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, so the external content directly controls prompts/instructions and is a required dependency.
Audit Metadata