← Back to Skills Marketplace
[Only test] Monitor Openclaw Server
by
Nguyen Thi Tham
· GitHub ↗
· v1.0.0
· MIT-0
134
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install test-monitor-openclaw-server
Description
A clean, reliable system resource monitor for CPU load, RAM, Swap, and Disk usage. Optimized for OpenClaw.
Usage Guidance
This skill runs a local shell script that gathers uptime, load, RAM, swap, and disk usage — that part is coherent. However, it then POSTs that information to a hard-coded third-party webhook (webhookrelay) without requiring any configuration or disclosing the recipient. Before installing or enabling this skill: 1) Treat it as exfiltration-capable — do not run it on sensitive or production hosts until you trust the webhook owner. 2) Ask the author to make the webhook configurable (or remove the POST), declare required binaries (curl), and document who receives the data. 3) If you need this functionality, prefer a version that requires you to supply your own webhook/API endpoint or API key and explicitly opt-in. 4) Run the script in a sandbox or network-restricted environment to observe traffic, or inspect/replace the curl line locally to prevent external transmission. Providing the skill author’s homepage or details about the webhook owner would raise confidence; absent that, treat it with caution.
Capability Analysis
Type: OpenClaw Skill
Name: test-monitor-openclaw-server
Version: 1.0.0
The skill includes a bash script (monitor.sh) that collects system telemetry (uptime, load, RAM, and disk usage) and automatically exfiltrates this data via a POST request to a hardcoded external webhook (bin.webhookrelay.com). While the data is low-sensitivity system stats, the hardcoded 'phone home' behavior to a third-party service without user configuration is a significant privacy risk and could be used for reconnaissance.
Capability Assessment
Purpose & Capability
The stated purpose (server resource monitoring) matches the included monitor.sh behavior (uptime, load, memory, disk). However, sending the collected metrics to an external webhook is a capability beyond simply reporting locally, and the webhook is hard-coded rather than configurable — that extra capability should be justified and declared.
Instruction Scope
SKILL.md says the agent executes monitor.sh, and monitor.sh collects local system info (uptime, free, df) — expected. But the script also unconditionally POSTs the gathered metrics to https://bin.webhookrelay.com/… (a third-party webhook). That transmits potentially sensitive host information to an external endpoint without any declared configuration, user approval, or credentials. The instructions do not warn users nor offer opt-in/opt-out or a configurable endpoint.
Install Mechanism
There is no install spec (instruction-only plus a script file). Nothing is downloaded or extracted. This low-install footprint is expected for such a simple monitor.
Credentials
The skill declares no required env vars or credentials, yet the script performs network transmission to an external service. It also uses curl but the skill metadata lists no required binaries. Sending metrics externally without requiring or documenting credentials/configuration is disproportionate to the stated purpose and reduces transparency.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system configuration, and does not persist credentials. Its runtime action is a one-off script execution when invoked, which is appropriate — the main concern is the network transmission, not persistence.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install test-monitor-openclaw-server - After installation, invoke the skill by name or use
/test-monitor-openclaw-server - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of a lightweight system resource monitor for OpenClaw:
- Reports CPU load (1, 5, 15 min averages), RAM, swap, and root disk usage.
- Displays server uptime.
- Uses native system calls for speed and reliability.
- Includes test sending of data to a monitoring server via webhook.
- Runs the local monitor.sh script to collect data.
Metadata
Frequently Asked Questions
What is [Only test] Monitor Openclaw Server?
A clean, reliable system resource monitor for CPU load, RAM, Swap, and Disk usage. Optimized for OpenClaw. It is an AI Agent Skill for Claude Code / OpenClaw, with 134 downloads so far.
How do I install [Only test] Monitor Openclaw Server?
Run "/install test-monitor-openclaw-server" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is [Only test] Monitor Openclaw Server free?
Yes, [Only test] Monitor Openclaw Server is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does [Only test] Monitor Openclaw Server support?
[Only test] Monitor Openclaw Server is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created [Only test] Monitor Openclaw Server?
It is built and maintained by Nguyen Thi Tham (@nguyenttham085); the current version is v1.0.0.
More Skills