orca-cli
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to resolve and execute a local CLI tool (
orca,orca-dev, ororca-ide) to perform system tasks. It includes explicit safety warnings to avoid accidental execution of system tools with similar names (e.g., the GNOME screen reader). - [INDIRECT_PROMPT_INJECTION]: The skill uses the command
ORCA skills get orca-clito load additional instructions into the agent's context at runtime. This mechanism allows the tool to provide version-specific guidance and is the intended primary functionality of the discovery stub. - Ingestion points: SKILL.md (via execution of
ORCA skills get orca-cli) - Boundary markers: None explicitly defined in the stub.
- Capability inventory: Subprocess execution of the
orcaCLI. - Sanitization: None.
Audit Metadata