web-design-guidelines

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required workflow fetches free-form guideline text from a public URL at runtime (outsider-authored web content via WebFetch), which is then read and used as LLM context for the rules.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs fetching runtime rules from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, and that fetched content directly controls the checker’s rules and output format used by the agent, making it a required external dependency.