orca-emulator-android
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes an
execcommand that permits the execution of arbitraryadb shellcommands on the target Android device or emulator. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, specifically the device's accessibility tree (
uiautomator) and system logs (logcat), which could potentially contain malicious content intended to influence agent behavior. - Ingestion points: Accessibility tree data via the
axcommand and system log data via thelogcatcommand inSKILL.md. - Boundary markers: No specific boundary markers or instructions to ignore embedded instructions in device output are defined.
- Capability inventory: The skill provides capabilities for APK installation (
install), app launching (launch), granting runtime permissions (permissions), and raw shell execution (exec) as seen inSKILL.md. - Sanitization: No sanitization or validation routines for device-derived data are described in the instructions.
Audit Metadata