orca-cli
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the local system by executing the
orcacommand-line interface or its variants (orca-ide,orca-dev). It includes logic to resolve the correct binary path based on environment variables (likeORCA_CLI_COMMANDorORCA_DEV_REPO_ROOT) and platform-specific contexts to ensure the agent targets the intended application. - [PROMPT_INJECTION]: The skill uses a dynamic loading pattern where the primary instructional guide is fetched from the local binary's output via
ORCA skills get orca-cli. This creates an indirect prompt injection surface where the agent's instructions are derived from runtime tool output. - Ingestion points: The output of the
ORCA skills get orca-clicommand (referenced in SKILL.md). - Boundary markers: The skill does not define specific boundary markers or instructions to ignore embedded commands in the binary output.
- Capability inventory: The skill has access to shell command execution and management of worktrees, terminals, and an embedded browser.
- Sanitization: No sanitization of the binary's output is performed before it is processed by the agent's context.
Audit Metadata