electron

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

• Third-party content exposure detected (high risk: 0.90). The skill's core workflow and "Webview Support" examples show the agent connecting to Electron app webviews (e.g., the tab list with https://app.slack.com/ and https://example.com/widget) and using snapshot/get text/click commands to read and act on that arbitrary third‑party/user‑generated content, which could contain instructions that influence subsequent actions.