orca-emulator
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute subcommands of the orca CLI (e.g., status, open, emulator list) to interact with mobile simulators. It includes logic to resolve the executable path based on environment variables like ORCA_CLI_COMMAND or ORCA_DEV_REPO_ROOT as described in SKILL.md.
- [INDIRECT_PROMPT_INJECTION]: The skill processes the output of the command ORCA skills get orca-emulator as a dynamic instruction guide, creating an attack surface for indirect prompt injection. 1. Ingestion points: Output of the ORCA skills get orca-emulator command. 2. Boundary markers: Absent; the agent is instructed to follow the command output instructions directly. 3. Capability inventory: Shell command execution and emulator management (taps, gestures, hardware buttons) via the orca tool. 4. Sanitization: Absent; the skill trusts the documentation served by the local binary.
Audit Metadata