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 Text and Get Source (documented in assets/examples/android-basic.robot and assets/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.md explains the use of mobile: shell via the Execute Script keyword, 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
Risk Level
SAFE
Analyzed
Mar 21, 2026, 05:17 PM