orca-cli
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local binaries (
orca,orca-ide, ororca-dev) to manage application state. It includes logic to avoid conflicts with the system screen reader on Linux by prioritizingorca-ide. - [DYNAMIC_EXECUTION]: The skill is designed to fetch and execute instructions generated at runtime via the
ORCA skills get orca-clicommand. This allows the binary to provide the primary operational logic to the agent dynamically. - [INDIRECT_PROMPT_INJECTION]: The skill processes content from potentially untrusted sources which creates an attack surface for indirect prompt injection.
- Ingestion points: Terminal output, browser content, and worktree comments handled by the Orca CLI.
- Boundary markers: No specific delimiters or "ignore" instructions are provided to the agent for the data read from these sources.
- Capability inventory: The skill allows terminal interaction (send/read), browser control, and file/worktree management.
- Sanitization: There is no evidence of sanitization or filtering of the content ingested from the external terminal or browser environments.
Audit Metadata