openclaw-management
Warn
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill extensively uses the
Bashtool to execute system commands for health monitoring, includingcurlfor local gateway checks,pm2for process management, anddf/dufor storage analysis. - [DYNAMIC_EXECUTION]: In the
/openclaw-manage autocommand, the skill dynamically writes a bash script to the file system at~/clawd/tools/openclaw-doctor-quick.shand subsequently executes it. It also usespython3 -cto execute inline code strings for processing JSON data from process managers. - [PERSISTENCE_MECHANISMS]: The skill attempts to maintain a continuous presence by scheduling its monitoring script via the
openclaw croncommand or instructing the user to manually modify the systemcrontabto run tasks every 15 minutes. - [PRIVILEGE_ESCALATION]: The skill modifies file permissions using
chmod +xon the scripts it generates to ensure they can be executed by the system scheduler. - [DATA_EXFILTRATION]: The monitoring script includes logic to send status reports and alerts to an external Discord channel using the
openclaw message sendcommand. While intended for administrative alerts, this establishes a pathway for sending internal system state data to an external service.
Audit Metadata