simulator-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill's Automation workflow instructs the agent to read the simulator's main webview output and console (GET /api/console and GET /api/screenshot/webview), which can contain arbitrary remote or user-generated web content loaded into the simulator and whose logs/screenshots are explicitly used to decide actions.