web-design-guidelines
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill explicitly fetches and uses rules from a public raw GitHub URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md) via WebFetch and reads/interprets that externally-hosted content as part of its workflow, exposing the agent to untrusted third-party content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill instructs the agent at runtime to fetch and apply rules from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, and that fetched content directly supplies the review rules and output-format instructions that control the agent's behavior, making it a required remote dependency.
Audit Metadata