mobile-emulator-start
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read terminal metadata and output tails from the file system (Phase A.1), which could be manipulated by adversarial external content.
- Ingestion points: Terminal metadata files (*.txt) containing command history, PIDs, and output tails located in project terminal directories.
- Boundary markers: No boundary markers or instructions to ignore embedded commands within the log data are provided.
- Capability inventory: The agent has the capability to execute
kill,taskkill,adb, andnpxcommands based on the instructions. - Sanitization: No sanitization or validation of the terminal output content is specified before the agent processes it.
- [COMMAND_EXECUTION]: The skill requires the agent to execute several shell commands to manage system processes and network configurations.
- Evidence: Use of
kill -9,taskkill /F,adb reverse,adb shell am start, andnpx expo startto manage development services and ports.
Audit Metadata