orca-automations

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to interact with the local environment using the orca or orca-ide CLI tools to create, list, and manage scheduled automations. This is the intended purpose of the skill and follows standard CLI interaction patterns.
  • [SAFE]: The documentation includes safety-conscious logic to prevent command collisions, such as recommending orca-ide on Linux systems to avoid triggering the GNOME screen reader (orca binary). It also emphasizes using --json flags for machine-readable output and querying --help to ensure command accuracy.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 08:59 AM
Security Audit — agent-trust-hub — orca-automations