web-design-guidelines

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

• Third-party content exposure detected (high risk: 0.95). The skill fetches public web content at runtime from the outsider-authored URL (https://raw.githubusercontent.com/.../command.md) and then ingests that fetched free-text into the agent’s LLM context to drive the review 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 which are retrieved at runtime and directly control the agent's checking logic and output format, making it a required external dependency.