ClawVault Skill
AI security system for OpenClaw with installation, rule generation, detection, and monitoring.
Protection Against:
- - Prompt injection attacks
- Data leakage (PII, credentials, API keys)
- Dangerous command execution
- Jailbreak attempts
Commands
/clawvault start
Start ClawVault services.
CODEBLOCK0
/clawvault install
Install ClawVault.
CODEBLOCK1
/clawvault health
Check service health and status.
CODEBLOCK2
/clawvault generate-rule
Generate security rules from natural language.
CODEBLOCK3
Scenarios: customer_service, development, production, INLINECODE3
/clawvault status
Get running status and statistics.
CODEBLOCK4
/clawvault test
Run detection tests.
CODEBLOCK5
Categories: all, sensitive, injection, INLINECODE7
/clawvault uninstall
Remove ClawVault.
CODEBLOCK6
Quick Examples
CODEBLOCK7
Requirements
- - Python 3.10+
- Ports 8765, 8766 available
Permissions
- -
execute_command - Run installation and ClawVault commands - INLINECODE9 - Create configuration files
- INLINECODE10 - Read configurations
- INLINECODE11 - Download packages and API calls
Security Considerations
⚠️ Important: ClawVault operates as a local HTTP proxy that inspects AI traffic.
What This Means:
- - ClawVault can see API requests, responses, and API keys
- This is intentional and necessary for threat detection
- All data stays on your local machine
Dashboard Security:
- - Default: Binds to
127.0.0.1 (localhost only) ✅ Secure - For remote access: Use SSH tunneling instead of exposing dashboard
- Example: INLINECODE13
Before Installing:
- - Review the SECURITY.md documentation
- Understand that ClawVault will inspect all proxied traffic
- Ensure dashboard binding is appropriate for your environment
- Consider running in isolated environment for sensitive use cases
For Production:
- - Use localhost-only dashboard
- Enable strict mode: INLINECODE14
- Configure audit log retention
- Review detection logs regularly
See SECURITY.md for complete security documentation.
Documentation
- - Full Guide: https://github.com/tophant-ai/ClawVault/blob/main/doc/OPENCLAWSKILL.md
- 中文文档: https://github.com/tophant-ai/ClawVault/blob/main/doc/zh/OPENCLAWSKILL.md
- Repository: https://github.com/tophant-ai/ClawVault
License
MIT © 2026 Tophant SPAI Lab
ClawVault 技能
用于 OpenClaw 的 AI 安全系统，具备安装、规则生成、检测和监控功能。
防护能力：
- - 提示注入攻击
- 数据泄露（PII、凭据、API 密钥）
- 危险命令执行
- 越狱尝试
命令
/clawvault start
启动 ClawVault 服务。
bash
clawvault start # 默认：仅本地主机（安全）
clawvault start --mode strict # 严格模式
/clawvault install
安装 ClawVault。
bash
/clawvault install --mode quick # 推荐
/clawvault install --mode standard # 交互式
/clawvault install --mode advanced # 完全控制
/clawvault health
检查服务健康状态。
bash
/clawvault health
/clawvault generate-rule
从自然语言生成安全规则。
bash
/clawvault generate-rule 阻止所有 AWS 凭据
/clawvault generate-rule --scenario customer_service --apply
场景： customer_service、development、production、finance
/clawvault status
获取运行状态和统计信息。
bash
/clawvault status
/clawvault test
运行检测测试。
bash
/clawvault test --category all
/clawvault test --category sensitive
类别： all、sensitive、injection、commands
/clawvault uninstall
卸载 ClawVault。
bash
/clawvault uninstall
/clawvault uninstall --keep-config # 保留配置
快速示例
bash
安装
/clawvault install --mode quick
生成规则
/clawvault generate-rule 检测数据库密码 --apply
应用场景
/clawvault generate-rule --scenario customer_service --apply
检查健康状态
/clawvault health
要求
- - Python 3.10+
- 端口 8765、8766 可用
权限
- - executecommand - 运行安装和 ClawVault 命令
- writefiles - 创建配置文件
- read_files - 读取配置
- network - 下载包和 API 调用
安全注意事项
⚠️ 重要： ClawVault 作为一个本地 HTTP 代理运行，用于检查 AI 流量。
这意味着什么：
- - ClawVault 可以看到 API 请求、响应和 API 密钥
- 这是有意为之，也是威胁检测所必需的
- 所有数据都保留在您的本地机器上
仪表盘安全：
- - 默认：绑定到 127.0.0.1（仅本地主机）✅ 安全
- 对于远程访问： 使用 SSH 隧道而不是暴露仪表盘
- 示例：ssh -L 8766:localhost:8766 user@server
安装前：
- - 查看 SECURITY.md 文档
- 了解 ClawVault 将检查所有代理流量
- 确保仪表盘绑定适合您的环境
- 对于敏感用例，考虑在隔离环境中运行
生产环境：
- - 使用仅本地主机仪表盘
- 启用严格模式：--mode strict
- 配置审计日志保留
- 定期检查检测日志
完整安全文档请参见 SECURITY.md。
文档
- - 完整指南：https://github.com/tophant-ai/ClawVault/blob/main/doc/OPENCLAWSKILL.md
- 中文文档：https://github.com/tophant-ai/ClawVault/blob/main/doc/zh/OPENCLAWSKILL.md
- 仓库：https://github.com/tophant-ai/ClawVault
许可证
MIT © 2026 Tophant SPAI Lab
