orca-cli
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute specific binaries (
orca,orca-dev, ororca-ide) based on environment variables likeORCA_CLI_COMMANDandORCA_DEV_REPO_ROOTto perform operations on worktrees, terminals, and repos. - [INDIRECT_PROMPT_INJECTION]: The skill utilizes a dynamic loading mechanism where it fetches a version-matched guide using the
ORCA skills get orca-clicommand to define further instructions for the agent. - Ingestion points: Data returned by the
ORCA skills getcommand is ingested into the agent context (SKILL.md). - Boundary markers: No explicit boundary markers or delimiters are defined to separate the dynamically fetched guide from other instructions.
- Capability inventory: The Orca CLI has access to the file system, shell terminals, and an embedded browser.
- Sanitization: The instructions do not specify any sanitization or validation of the guide content retrieved from the CLI.
Audit Metadata