Install
openclaw skills install claw-security-suiteProvides four-layer security for OpenClaw including static code scanning, logic audit, runtime protection, and periodic security patrols with automated reports.
openclaw skills install claw-security-suite🛡️ OpenClaw 完整四层纵深安全防御体系
为 OpenClaw 提供从静态扫描到运行时防护的完整安全保障
| 层级 | 功能 | 说明 |
|---|---|---|
| 第一层 | 静态代码扫描 | 安装前扫描,检测恶意代码、硬编码密钥、危险系统调用 |
| 第二层 | 逻辑安全审计 | 分析代码逻辑是否越权,检查是否符合最小权限原则 |
| 第三层 | 运行时实时防护 | 检测并阻止提示注入、命令注入、SSRF等攻击,自动净化输入 |
| 第四层 | 定期安全巡检 | 每日自动巡检、每周全量扫描、基线完整性保护 |
CLAW_SECURITY_CLOUD_ENDPOINT 启用云端情报校验默认内置提供腾讯云 ClawScan 云端情报接口,会查询已公开的技能安全信誉数据:
CLAW_SECURITY_CLOUD_ENDPOINT 环境变量修改端点openclaw-security-suite/
├── SKILL.md # 本文档
├── _meta.json # Skill元数据
├── lib/
│ ├── static_scanner.py # 第一层:静态代码扫描
│ ├── logic_auditor.py # 第二层:逻辑安全审计
│ ├── runtime_protector.py # 第三层:运行时防护
│ └── security_patrol.py # 第四层:定期巡检
└── references/
└── security_policy.md # 安全安装策略
from skills.claw-security-suite.lib.static_scanner import scan
# 带云端情报校验扫描(推荐)
result = scan(extracted_path, skill_name="your-skill-slug", source="clawhub")
if not result.is_safe:
# 拦截安装
print(result.to_report())
# 仅本地扫描(不联网)
result = scan(extracted_path)
static_scanner.scan(zip_path)logic_auditor.audit(extracted_path)每次用户输入前自动调用:
from skills.openclaw-security-suite.lib.runtime_protector import RuntimeProtector
result = RuntimeProtector.check(user_input)
if result.is_malicious:
# 拒绝请求
logger.warning(f"Blocked malicious request: {result.reason}")
else:
# 净化后继续处理
clean_input = result.clean_input
from skills.openclaw-security-suite.lib.security_patrol import daily_patrol
daily_patrol.run()
from skills.openclaw-security-suite.lib.security_patrol import weekly_scan
weekly_scan.run()
/app/working/.env 除非是安全审计本身Kenz1117
MIT-0 (MIT No Attribution)