orca-cli
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill identifies and executes local command-line tools (such as
orca,orca-ide, ororca-dev) depending on the environment state to manage worktrees, terminals, and artifacts. - [PROMPT_INJECTION]: The instructions direct the agent to load its full operational guide dynamically via the
ORCA skills get orca-clicommand, which bypasses static analysis. - Ingestion points: The agent ingests the stdout of the
ORCAbinary directly into its instruction context. - Boundary markers: The skill does not provide delimiters or instructions to the agent to treat the binary output as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill has the capability to perform shell command execution and filesystem operations through the resolved
ORCAbinary. - Sanitization: There is no evidence of filtering, escaping, or validation performed on the CLI output before the agent processes it as instructions.
Audit Metadata