browser-extension-builder

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

• Third-party content exposure detected (high risk: 0.90). The skill's patterns explicitly run content scripts on web pages (references/patterns.md: "content.js
• Runs on every matched page", injecting UI and reading document/querySelector, and the manifest example uses "matches": ["<all_urls>"]), so the agent is expected to read and interpret arbitrary public web page content.