The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to resolve and execute local binaries, specifically orca, orca-ide, or orca-dev, to manage worktrees, terminals, and internal automations.
[INDIRECT_PROMPT_INJECTION]: The skill uses a dynamic instruction loading pattern where it fetches its primary usage guide from the output of the shell command ORCA skills get orca-cli at runtime. * Ingestion points: The output of ORCA skills get orca-cli is consumed as active instructions in SKILL.md. * Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within the dynamic tool output. * Capability inventory: The agent is granted capabilities to execute shell commands, manage worktrees, and control an embedded browser. * Sanitization: There is no evidence of output validation or sanitization before the agent interprets the CLI output as instructions.

orca-cli