android-emulator
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The core functionality of the skill is provided by
scripts/emu.sh, which executes various system commands to interact with the Android development environment. This includesadbfor device communication,emulatorfor managing the AVD lifecycle,flutter(orfvm) for building and running the app, andncfor sending commands to the local qemu console. - [DATA_EXFILTRATION]: The skill accesses
~/.emulator_console_auth_tokento retrieve the authentication token required for the local emulator console. This is a standard procedure for local emulator automation. The token is used strictly for communication withlocalhostto enable advanced input features like multi-touch pinching, which are not available through standardadbcommands. - [INDIRECT_PROMPT_INJECTION]: The
ui-list,ui-find, andtap-labelcommands ingest the Android accessibility tree (viauiautomator dump). This represents an attack surface where an application's UI labels could contain instructions for the agent. However, the skill treats these labels as data for matching purposes and does not directly execute them, and the risk is considered low given the local development context. - [DYNAMIC_EXECUTION]: The script
scripts/emu.shutilizes embedded Python code blocks to perform XML parsing and coordinate resolution. These blocks are hardcoded within the script and do not incorporate untrusted external input into the executable logic.
Audit Metadata