The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of local binaries (orca, orca-ide, or orca-dev) to manage development environments and retrieve documentation. These operations are restricted to the local system and the specific toolset described.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch its primary operating instructions from the output of a local command (ORCA skills get orca-cli). While this creates a potential surface for instructions to be influenced by the binary's output, it is a standard mechanism for keeping documentation in sync with the tool version.
Ingestion points: The agent processes output from the ORCA skills get orca-cli command as instructions for subsequent tasks.
Boundary markers: None identified; the agent is directed to read the output directly to understand available subcommands and flags.
Capability inventory: The skill uses subprocess calls to execute the Orca CLI and its subcommands (status, worktree ps, terminal list, etc.) as defined in SKILL.md.
Sanitization: No explicit sanitization or validation of the CLI output is performed before the agent adopts the retrieved instructions.

orca-cli