adb
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to interact with external Android devices, which constitutes a data ingestion surface for potentially untrusted content from the device environment.
- Ingestion points: The agent is directed to read device logs, access files, and observe runtime states from an authorized Android emulator or test device.
- Boundary markers: The instructions do not specify the use of delimiters or clear boundaries to separate data retrieved from the device from the agent's internal instructions.
- Capability inventory: The skill involves powerful capabilities including package installation, file system access, log retrieval, and network port forwarding via ADB.
- Sanitization: There are no instructions for sanitizing, escaping, or validating the external data (such as log entries or file content) before it is processed in the agent's context.
Audit Metadata