Real-time dashboard for monitoring OpenClaw devices, agents, sessions, cron jobs, models, and token usage with English/Chinese interface.

This package appears to be what it says (a monitoring dashboard) but you should review and limit exposure before installing. Steps to consider: - Inspect ~/.openclaw contents on the host (openclaw.json, sessions, agents, cron runs) to understand what sensitive data would be visible to the dashboard. - Run the service bound to localhost (avoid the example 0.0.0.0) or behind a firewall/reverse proxy that requires auth, especially if .openclaw contains tokens. - Review the full clawstatus.py source (it is included) to confirm there are no unexpected network callbacks or external endpoints; the code runs the local 'openclaw' CLI and probes the gateway port. - Note the code honors OPENCLAW_BIN and CLAWSTATUS_ENABLE_STATUS_USAGE env vars — set these deliberately or leave unset; do not point OPENCLAW_BIN to unknown binaries. - Consider running in an isolated environment (container or dedicated monitoring host) and limit filesystem permissions so the process can only read the OpenClaw-related paths it needs. If you want, provide the rest of clawstatus.py (truncated in the listing) and I can re-check for any hidden endpoints or data-exfiltration code to increase confidence.

Type: OpenClaw Skill Name: clawstatus Version: 1.0.0 The ClawStatus bundle provides a comprehensive management dashboard for the OpenClaw ecosystem but includes high-risk administrative capabilities. Specifically, 'clawstatus.py' uses the subprocess module to execute system commands, including 'systemctl' for service restarts and 'openclaw' for triggering or deleting cron jobs. It also performs atomic writes to the core 'openclaw.json' configuration file to modify agent models. While these features are consistent with the tool's stated purpose, the application is unauthenticated by default (the 'required_token' is explicitly set to None in 'create_app'), which could allow unauthorized users to tamper with the system configuration or execute arbitrary OpenClaw tasks if the port is exposed. No evidence of intentional malice or data exfiltration was found.