android-cli-ui-automation-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly launches arbitrary URLs on the device ("adb ... am start -a android.intent.action.VIEW -d ''" in SKILL.md/README) and directs the agent to observe WebView/browser page content via layout or screenshots, so the agent will ingest untrusted public webpage content that could carry instructions affecting its actions.