The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides logic to resolve an executable (referred to as ORCA) from the local environment using variables like ORCA_CLI_COMMAND and ORCA_DEV_REPO_ROOT, or platform-specific names like orca-ide. It then instructs the agent to run commands like ORCA skills get and ORCA open to manage simulators.
[INDIRECT_PROMPT_INJECTION]: The skill fetches external instructions at runtime, which represents a potential injection surface for instructions embedded in tool output. • Ingestion points: The output of the shell command ORCA skills get orca-emulator is loaded into the agent's context as a guide. • Boundary markers: No explicit delimiters are specified to separate the fetched guide content from the agent's internal instructions. • Capability inventory: The skill enables shell command execution and interaction with macOS/iOS simulator tools via the ORCA binary. • Sanitization: The skill does not implement validation or sanitization for the content returned by the guide command.

orca-emulator