The Agent Skills Directory

[COMMAND_EXECUTION]: The skill resolves and executes local shell commands using various Orca CLI binaries (orca, orca-dev, orca-ide). It specifically warns against running the bare orca command on Linux systems to avoid accidental execution of the GNOME screen reader.
[INDIRECT_PROMPT_INJECTION]: The skill implements a 'discovery stub' pattern where it instructs the agent to dynamically load its full operational guide via the command ORCA skills get orca-cli. This output is treated as the source of truth for subsequent agent actions.
Ingestion points: The primary ingestion point is the standard output of the ORCA skills get orca-cli command.
Boundary markers: The skill does not provide any delimiters or instructions for the agent to ignore potentially malicious content embedded in the fetched guide.
Capability inventory: The skill grants the agent control over Orca-managed worktrees, terminals, repositories, automations, and an embedded browser. It also includes 'handoff' capabilities to transfer tasks to other agents.
Sanitization: There is no evidence of sanitization, validation, or schema enforcement on the data returned by the CLI before it is integrated into the agent's context.

orca-cli