web-design-guidelines

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads live rules from a public URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md) and uses that fetched, third‑party content as authoritative input for its review, exposing the agent to untrusted external content that could contain injected instructions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to fetch runtime guidelines from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and to apply the fetched rules and output-format instructions on each review, so the remote content directly controls the agent's prompts/behavior and is a required runtime dependency.