debugging

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

• Third-party content exposure detected (high risk: 0.70). The required workflow ingests runtime crash/Gradle/logcat/Crashlytics evidence (e.g., “Logcat output” and “Crashlytics reports”) which are typically outsider-authored text from external systems/users, and the agent will read that free-form prose into the LLM context during triage.