orca-emulator-android

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill serves as an interface for executing Android Debug Bridge (adb) commands.
  • The exec command specifically enables running arbitrary shell commands on a connected Android device or emulator.
  • Other commands automate standard developer actions such as installing APKs, launching activities, and adjusting runtime permissions.
  • [DATA_EXFILTRATION]: The skill provides capabilities to ingest data from the device into the agent's context for processing.
  • ORCA emulator logcat retrieves system and application logs.
  • ORCA emulator ax captures the UI accessibility tree via uiautomator to enable screen analysis.
  • [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection because it ingests untrusted data from external sources (device logs and UI trees).
  • Ingestion points: UI accessibility tree (ax) and system logs (logcat) are read into the agent's context.
  • Boundary markers: The skill does not explicitly define delimiters for these data streams in the provided instructions.
  • Capability inventory: The skill possesses significant capabilities including arbitrary shell execution on the device (exec), UI input injection (tap, type), and app management (install, launch).
  • Sanitization: There is no mention of sanitizing or escaping the data retrieved from the device before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 04:04 PM
Security Audit — agent-trust-hub — orca-emulator-android