OpenClaw Dashboard

Use when the user wants a local visual operations dashboard for OpenClaw, with a cute robot presentation, live status visibility, chat access, efficiency tre...

Do not run install_launchd.sh or start_bg.sh until you have the missing Python runtime files (server.py, autoheal.py, app_watchdog.py) and have reviewed them. The installer will create persistent macOS LaunchAgents that auto-restart Python processes. Specifically: 1) Verify server.py and the other referenced Python scripts exist and inspect them for network activity, credential access, or code that reads/writes ~/.openclaw or other sensitive paths. 2) Confirm the package origin (repository URL and author) and prefer running in an isolated test account or VM first. 3) If you only want a one-off local demo, use ./run_monitor.sh (foreground) rather than installing launchd services. 4) If you find code that reads session files or makes outbound connections, treat that as a red flag unless you explicitly expect that behavior. If you cannot obtain or review the missing Python files, avoid installing the launchd services — the package cannot be fully audited as provided.

Type: OpenClaw Skill Name: openclaw-dashboard-local Version: 1.0.2 The skill bundle implements persistent background services on macOS by installing multiple launchd agents (install_launchd.sh) to run a local web server, an 'auto-heal' script, and a watchdog. While these capabilities are aligned with the stated purpose of providing a persistent monitoring dashboard (SKILL.md), the automated setup of persistence and the background execution of scripts whose full logic is not provided (server.py, autoheal.py, app_watchdog.py) constitute high-risk behavior. No clear evidence of intentional malice or data exfiltration was found in the provided shell scripts or documentation.