cancel
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to manage processes using standard system tools such as find, ps, tasklist, and tmux. It also executes a local Node.js script located within the plugin's root directory to clean up orphan processes.
- [SAFE]: File system operations are confined to the .omc/state/ and ~/.claude/ directories for the purpose of removing session state and legacy artifacts. These actions are consistent with the skill's primary function of environment cleanup.
- [SAFE]: Communication for team shutdown is conducted through an internal messaging protocol (SendMessage) within the platform, with no external network dependencies or exfiltration risks identified.
Audit Metadata