skills/stablyai/orca/orca-cli/Gen Agent Trust Hub

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 instructs the agent to resolve and execute local CLI tools (orca, orca-ide, or orca-dev) to manage worktrees, terminals, and artifacts. This is the primary intended function of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to load a version-matched guide via the command ORCA skills get orca-cli, which then dictates further agent behavior.
  • Ingestion points: The output of the skills get command is used to provide instructions for subsequent operations.
  • Boundary markers: None provided; the skill relies on the local tool's output to guide the session.
  • Capability inventory: The skill uses subprocess execution to interact with the CLI.
  • Sanitization: The skill instructs the agent to use --help for discovery and to stop if errors occur, providing a basic form of verification, though it does not explicitly sanitize the text output of the guide.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:33 PM
Security Audit — agent-trust-hub — orca-cli