orca-emulator-android

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to resolve and execute the orca CLI (or variants like orca-dev, orca-ide) to manage Android emulators and devices through adb.
  • [DYNAMIC_EXECUTION]: The skill uses a bootstrap pattern where it executes ORCA skills get orca-emulator-android to dynamically load its primary instruction set into the agent's context at runtime.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting and following instructions produced by the output of an external command.
  • Ingestion points: The output of the ORCA skills get orca-emulator-android command is explicitly treated as the "full guide" for the agent to follow.
  • Boundary markers: The provided stub does not define boundary markers or "ignore" instructions for the dynamically loaded content.
  • Capability inventory: The skill uses the orca CLI to perform high-privilege operations such as app installation, hardware button control, and access to the Android accessibility tree and logcat.
  • Sanitization: No sanitization or validation of the CLI output is described before the agent adopts it as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 01:23 AM
Security Audit — agent-trust-hub — orca-emulator-android