openclaw-control
控制和管理 OpenClaw AI 助手。用于发送消息给 OpenClaw、检查状态、管理配置和安装技能。当用户想要与 OpenClaw 交互或管理 OpenClaw 时使用此技能。
How do I install this agent skill?
npx skills add https://github.com/rtgs2017/nagaagent --skill openclaw-controlIs this agent skill safe to install?
- Gen Agent Trust Hubfail
The 'openclaw-control' skill enables the management of the OpenClaw AI assistant. It is highly vulnerable to Indirect Prompt Injection because it forwards raw user messages directly to an external execution environment without sanitization. It also exposes high-privilege capabilities such as gateway management and configuration modification.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
- Runlayerwarn
1/1 file flagged
What does this agent skill do?
OpenClaw 控制技能
本技能让你能够控制和管理 OpenClaw AI 助手。
核心能力
1. 发送消息给 OpenClaw
通过 Naga 的 Agent Server API 向 OpenClaw 发送任务:
POST /openclaw/send
{
"message": "你的消息内容",
"wake_mode": "now" // 立即执行
}
2. 检查 OpenClaw 状态
GET /openclaw/health- 健康检查GET /openclaw/status- 运行状态GET /openclaw/session- 会话信息
3. 管理 Gateway
POST /openclaw/gateway/start- 启动POST /openclaw/gateway/stop- 停止POST /openclaw/gateway/restart- 重启GET /openclaw/gateway/status- 状态
4. 配置管理
GET /openclaw/config- 获取配置POST /openclaw/config/model- 设置模型POST /openclaw/config/hooks- 配置 Hooks
使用流程
- 检查连接: 先调用健康检查确认 OpenClaw 可用
- 发送任务: 使用
/openclaw/send发送消息 - 监控结果: 通过
/openclaw/history查看执行结果
注意事项
- OpenClaw 默认运行在
http://127.0.0.1:18789 - 需要配置 Hooks Token 才能发送消息
- 建议使用免费的 GLM-4.7 模型进行测试
示例
让 OpenClaw 执行任务
{
"message": "帮我整理桌面上的文件,按类型分类",
"wake_mode": "now"
}
查询当前状态
调用 GET /openclaw/status 获取 OpenClaw 当前正在做什么。
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/rtgs2017/nagaagent/openclaw-control">View openclaw-control on skillZs</a>