← 返回 Skills 市场
Auto Monitor - System Monitoring
作者
xaiohuangningde
· GitHub ↗
· v1.0.0
4168
总下载
1
收藏
36
当前安装
1
版本数
在 OpenClaw 中安装
/install auto-monitor
功能描述
主动监控系统状态。定期检查服务器健康，主动汇报，无需等待指令。
安全使用建议
Install only if you intend to give an agent proactive system-monitoring authority. Use read-only monitoring by default, define the exact hosts and interval, and require explicit confirmation before any restart, deletion, configuration change, process kill, or other repair action.
功能分析
Type: OpenClaw Skill
Name: auto-monitor
Version: 1.0.0
The `SKILL.md` file, which provides instructions to the AI agent, contains a highly risky directive: '可以自动修复的立刻处理' (Immediately handles issues that can be automatically fixed). This instruction grants the agent broad, proactive execution capabilities to modify the system without explicit, per-action user consent. While the stated purpose is benign (system maintenance), this design introduces a significant vulnerability, as it could lead to unintended system changes, data loss, or be exploited for arbitrary command execution if the 'auto-fix' logic is flawed or compromised. This is a critical RCE risk inherent in the skill's design, classifying it as suspicious rather than malicious due to the lack of explicit intent for harm in the provided files.
能力评估
Purpose & Capability
Monitoring disk, memory, CPU, network, and processes matches the stated purpose, but the instruction to immediately fix automatically repairable issues expands the skill into unspecified system-changing remediation.
Instruction Scope
The skill says to check periodically and report proactively, but does not define target systems, schedule, reporting destination, authorization, safe actions, or confirmation requirements.
Install Mechanism
The artifact contains only SKILL.md and skill.json; there are no scripts, binaries, package installs, or install-time execution paths.
Credentials
Read-only health checks are proportionate for monitoring, but undefined automatic repair could affect processes, configuration, data, or service availability depending on the agent's environment.
Persistence & Privilege
The instructions imply ongoing recurring operation every N minutes and proactive action, with no opt-in boundary, stop condition, privilege limit, audit log, or rollback expectation.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install auto-monitor - 安装完成后，直接呼叫该 Skill 的名称或使用
/auto-monitor触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of auto-monitor: proactive system status monitoring and reporting.
- Periodically checks disk, memory, CPU, network, and process status.
- Automatically generates health reports and sends alerts when thresholds are exceeded.
- Alerts triggered for disk usage >80%, memory >85%, or CPU load > (cores × 0.8).
- Proactively reports issues without waiting for user inquiries.
- Supports immediate auto-remediation for fixable problems.
元数据
常见问题
Auto Monitor - System Monitoring 是什么？
主动监控系统状态。定期检查服务器健康，主动汇报，无需等待指令。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 4168 次。
如何安装 Auto Monitor - System Monitoring？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install auto-monitor」即可一键安装，无需额外配置。
Auto Monitor - System Monitoring 是免费的吗？
是的，Auto Monitor - System Monitoring 完全免费（开源免费），可自由下载、安装和使用。
Auto Monitor - System Monitoring 支持哪些平台？
Auto Monitor - System Monitoring 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Auto Monitor - System Monitoring？
由 xaiohuangningde（@xaiohuangningde）开发并维护，当前版本 v1.0.0。
推荐 Skills