appium
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it provides keywords like
Get TextandGet Source(documented inassets/examples/android-basic.robotandassets/examples/hybrid-app.robot) which ingest untrusted data from third-party mobile applications into the agent context. There are no boundary markers or sanitization instructions to mitigate the risk of an agent following malicious commands embedded within an application's UI. - [COMMAND_EXECUTION]: The documentation in
references/android-specific.mdexplains the use ofmobile: shellvia theExecute Scriptkeyword, which allows the execution of arbitrary shell commands on a connected Android device. While this is a standard feature for advanced mobile automation, it provides a high-privilege interface to the device's operating system.
Audit Metadata