📡 Monitor — 监控告警
v1.0.2用户可自定义监控对象，技能自动安排检测周期并推送告警，实现全天候无代码监控。
2· 1.6k·12 当前·12 累计
by 下载技能包
最后更新
2026/4/22
安全扫描
OpenClaw
安全
high confidenceThe skill's requested tools, storage, and behavior are consistent with a local monitoring/alerting utility, but it will create files under ~/monitor, execute the checks you ask for (including user-supplied commands), and can send alerts to endpoints you provide — review definitions and targets before use.
评估建议
Before installing, review and control these points:
- Inspect monitor definitions (~/monitor/monitors.json) and avoid storing secrets (API keys, auth headers) in plain JSON. Use environment variables or secure stores where possible.
- Be cautious with 'custom' checks: they run arbitrary commands you supply. Do not add untrusted commands that could access or transmit sensitive data.
- Only provide webhook URLs or channels you trust. Alert payloads may include status, timestamps, and any logged o...详细分析 ▾
✓ 用途与能力
Name/description match the declared requirements: only curl is required for HTTP checks, other tools are optional for specific check types. Storing monitors and logs under ~/monitor is consistent with a local monitor skill.
ℹ 指令范围
SKILL.md stays within monitoring scope but explicitly allows running user-provided commands (custom checks) and will post alert payloads to user-supplied webhooks or Pushover. These behaviors are expected for a monitor but grant the agent the ability to execute arbitrary commands you provide and to transmit alert data to external endpoints — review any custom commands and webhook targets.
✓ 安装机制
Instruction-only skill with no install step and no code files; nothing is downloaded or written at install time beyond the runtime-created ~/monitor directory. Low install risk.
✓ 凭证需求
No required credentials. Optional env vars (PUSHOVER_TOKEN, PUSHOVER_USER) are declared and used only for Pushover alerts. No unexpected secrets or unrelated credentials are requested.
ℹ 持久化与权限
Skill is not force-installed (always:false) but will create and write to ~/monitor/monitors.json, config.json, and logs. The agent may autonomously run scheduled checks (platform default); this is expected for a monitoring skill but increases the impact of any misconfiguration (e.g., a webhook that accepts sensitive data).
安全有层次，运行前请审查代码。
运行时依赖
🖥️ OSLinux · macOS · Windows
版本
latestv1.0.22026/2/11
Declared required binaries and optional env vars in metadata
● 可疑
安装命令
点击复制官方npx clawhub@latest install monitor
镜像加速npx clawhub@latest install monitor --registry https://cn.longxiaskill.com