web-design-guidelines

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 WebFetch and consume live rules and output-format instructions from an open public URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md), meaning arbitrary third-party content will be read and can directly control the agent's checks and output behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires fetching and using the remote guidelines at runtime via https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, and states the fetched content contains the rules and output-format instructions that directly control the agent's behavior.