The Agent Skills Directory

[PROMPT_INJECTION]: The skill implements an indirect prompt injection surface through its 'discovery stub' design. Instead of containing all instructions, it directs the agent to execute ORCA skills get orca-cli and follow the resulting output.
Ingestion points: The output of the runtime command ORCA skills get orca-cli serves as the primary source of instructions for the agent (SKILL.md).
Boundary markers: Absent. The agent is not provided with delimiters or instructions to treat the CLI output as untrusted data.
Capability inventory: The skill enables full interaction with the Orca CLI, which includes capabilities for managing terminals, worktrees, and an embedded browser (SKILL.md).
Sanitization: Absent. There is no verification or filtering of the instructions returned by the CLI tool before the agent acts upon them.
[COMMAND_EXECUTION]: The skill's primary function is the execution of the orca command-line interface. It includes specific logic to resolve the correct executable path (orca, orca-ide, or orca-dev) based on environment variables like ORCA_CLI_COMMAND and ORCA_DEV_REPO_ROOT and system configuration.

orca-cli