The Agent Skills Directory

[PRIVILEGE_ESCALATION]: The skill explicitly instructs the agent to re-run commands with escalated permissions if it encounters a 'runtime_access_denied' error, which constitutes an instruction to bypass sandbox constraints.\n- [COMMAND_EXECUTION]: The skill resolves and executes local binaries including orca, orca-ide, and orca-dev based on environment variables like ORCA_CLI_COMMAND or ORCA_DEV_REPO_ROOT.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests guidance at runtime through the ORCA skills get orca-cli command, which allows external tool output to influence agent behavior.\n
Ingestion points: Data fetched via the ORCA skills get orca-cli command described in SKILL.md.\n
Boundary markers: None identified in the provided instructions.\n
Capability inventory: The skill allows execution of system commands, terminal management, and browser control via the Orca CLI.\n
Sanitization: No validation or sanitization of the runtime-fetched guide is mentioned.

orca-cli