mobile-emulator-test
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill includes instructions to discover sensitive configuration data by searching through project files like .env and .env.local for Supabase and Sentry credentials. It also retrieves user metadata from the auth.users table via SQL queries during authentication testing.- [COMMAND_EXECUTION]: The skill makes extensive use of system commands for environment management and debugging, including process termination (kill, taskkill), mobile package management (npx expo, gradlew), and direct interaction with the Android emulator using adb shell.- [PROMPT_INJECTION]: The skill manages an indirect prompt injection surface by ingesting data from external sources that could contain malicious instructions.
- Ingestion points: The agent is instructed to read and process output from adb logcat, uiautomator UI dumps, Supabase SQL results, and local email service outputs.
- Boundary markers: The instructions do not define explicit delimiters or instructions to ignore potential commands embedded in the ingested data.
- Capability inventory: The agent maintains the ability to execute shell commands, perform database mutations, and capture screen data.
- Sanitization: No sanitization or validation steps are included for data retrieved from external ingestion points before it enters the agent context.
Audit Metadata