quick-deploy

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

• Third-party content exposure detected (high risk: 0.80). The skill's deployment workflow explicitly fetches public URLs to verify deployments (e.g., Step 5 Vercel verification: "npx vercel list" and "curl 项目域名检查是否返回 200", and the Cloudflare Worker verification "curl https://your-worker..."), which causes the agent to read and act on open/public third‑party web responses as part of its decision-making.