orca-cli
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to interact with the
orcacommand-line interface. It includes specific logic to determine which executable to run based on environment variables such asORCA_CLI_COMMANDorORCA_DEV_REPO_ROOT, or by checking the operating system environment. - [INDIRECT_PROMPT_INJECTION]: The skill uses an ingestion point where it loads its full guide at runtime via the shell command
ORCA skills get orca-cli. - Ingestion points: The output of the
ORCA skills get orca-clicommand is processed as instructions by the agent. - Boundary markers: No explicit boundary markers or instructions to ignore potential injections within the tool output are present.
- Capability inventory: The
orcatool has broad capabilities including managing terminals, file system worktrees, and controlling an embedded browser. - Sanitization: There is no evidence of sanitization or validation performed on the output returned by the external command before the agent interprets it.
Audit Metadata