web-design-guidelines
Warn
Audited by Snyk on Mar 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and use rules from a public URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md) via WebFetch, so it will ingest untrusted third‑party content from the open web and apply those instructions to drive its review and output format.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill uses WebFetch at runtime to load guidance from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, and that fetched content is read each run to supply the rules and output-format instructions that directly control the agent's behavior.
Audit Metadata