mobile-mcp
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run various system commands including adb, xcrun, yarn, gradlew, and lsof to interact with mobile devices and manage build processes.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @mobilenext/mobile-mcp package from the NPM registry using the npx command.
- [DATA_EXFILTRATION]: The skill provides tools for capturing screenshots and reading system logs (adb logcat), which can expose sensitive information displayed on or generated by the mobile device during automation sessions.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. Ingestion points: The agent retrieves untrusted data from the mobile device's UI elements via mobile_list_elements_on_screen and from system logs via adb logcat. Boundary markers: The instructions do not define clear boundaries or provide warnings to the agent to ignore instructions embedded within the application UI or logs. Capability inventory: The agent has the ability to execute shell commands, open URLs on the device, and interact with the UI through tapping and typing. Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the device before it is processed by the agent.
Audit Metadata