setup-deploy

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly contacts and inspects arbitrary public deployment URLs and external platform CLIs as part of its workflow (e.g., Step 5's curl health-check of the user-provided production URL and platform checks like vercel ls --prod / fly status), which ingests untrusted third-party responses that can influence subsequent actions.