Operator Dashboard
PassAudited by ClawScan on May 3, 2026.
Overview
The skill is a coherent OpenClaw monitoring assistant, but it relies on local command execution, scheduled/proactive alerts, and channel messaging that users should knowingly enable.
This skill appears safe for its stated monitoring purpose if you want OpenClaw health checks and alerts. Before installing, make sure the alert channel is appropriate, understand that it runs local diagnostic commands, and require explicit command-level confirmation before approving any repair or cleanup action.
Findings (5)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may run diagnostic commands on the host and read operational status information.
The skill tells the agent to run local commands to inspect OpenClaw and host health. This is central to the monitoring purpose, but it is still local command execution.
Gateway health — `exec: openclaw status` and `exec: openclaw health --json` ... Disk/memory usage — `exec: df -h /` and `exec: free -m`.
Install only if you want the skill to inspect the local OpenClaw environment, and review any proposed repair action before approving it.
If approved, fixes could restart services, retry jobs, or remove temporary/log files.
The skill may propose actions that modify the system or service state, but the artifact explicitly requires user approval before deleting, restarting, or modifying anything.
Offer "fix it" capability ... Log rotation for high disk usage. Restarting a failed service. Retrying a failed cron job. Clearing temporary files. ... Ask before any destructive action
Require the agent to state the exact command or change before approving a fix, especially for deletion, cleanup, or restart actions.
Gateway failures, cron issues, plugin health, and resource usage may be posted into the active chat/channel.
The skill sends monitoring alerts through the current conversation channel. This is disclosed and purpose-aligned, but the alert content may contain operational details.
Use the `message` tool for proactive alerts, but only when you have a valid target (the current chat).
Use this skill only in a channel where operational health information is appropriate to share.
The user may receive daily summaries and immediate critical alerts without manually asking each time.
The skill is designed for scheduled and proactive behavior. This is the stated purpose of a monitoring dashboard, but it means the agent may send messages outside a direct user request.
Routine daily summary (once per day via cron) ... Severity-based immediate alerts — if any of these occur, notify the user immediately
Confirm the intended cron schedule, target channel, and quiet-hours behavior before relying on proactive alerts.
There may be confusion about how the skill chooses the alert destination, especially for cron-triggered summaries.
The channel-detection description is internally inconsistent. The later instruction narrows behavior to the current conversation, but users should verify where scheduled alerts will be sent.
detects your channel from OpenClaw config ... MUST NOT ... Parse OpenClaw config for channel detection — rely on the current conversation context.
Before enabling scheduled summaries, explicitly configure or confirm the destination channel.