devops

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

• Third-party content exposure detected (high risk: 0.90). The skill's browser-rendering and advanced Workers references (references/browser-rendering.md and references/cloudflare-workers-advanced.md) show Puppeteer code that navigates to arbitrary public URLs (e.g., page.goto('https://news.ycombinator.com') and page.goto(message.body.url')), scrapes page.content, and passes that untrusted user-generated/third-party HTML into an AI (Ai.run) and queueing logic, so external web content is ingested and can materially influence agent actions.