web-design-guidelines

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

• Third-party content exposure detected (high risk: 1.00). This skill's required workflow (SKILL.md) instructs the agent to WebFetch and read live guidelines from a public raw GitHub URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md), so untrusted third-party content is fetched and can directly influence rule interpretation and output behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs fetching and using the live guidelines from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md at runtime as the authoritative rules/output format that directly control the agent's behavior, and that fetch is required for each review.