openclaw-security-scanner

扫描 OpenClaw 配置权限和安全隐患。当用户提到"安全扫描"、"权限检查"、"安全检查"、"扫描权限"、"检查配置安全"时使用此技能。输出具体漏洞内容、安全评分和修复建议,支持交互式一键修复。

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "openclaw-security-scanner" with this command: npx skills add ithacajason/jason-openclaw-security-scanner

OpenClaw 安全扫描器

扫描 OpenClaw 的配置、文件权限、敏感信息泄露,生成安全报告并支持交互式修复。

使用方法

# 扫描并显示报告
python3 scripts/scan_security.py

# 交互式修复(逐个询问)
python3 scripts/scan_security.py --interactive

# 自动修复所有问题
python3 scripts/scan_security.py --fix-all

# 修复指定问题
python3 scripts/scan_security.py --fix 0

扫描内容

类别检查项自动修复
操作规则删除操作是否需人工确认✅ 添加规则
配置权限子代理权限、沙箱状态、公网暴露部分
文件权限目录权限✅ chmod
敏感信息API Key、密码、Token、私钥泄露✅ .gitignore
日志审计错误统计、认证失败❌ 仅提醒

工作流程

  1. 扫描 - 检测所有安全隐患
  2. 报告 - 显示安全评分和详细问题
  3. 修复建议 - 针对每个问题给出具体修复方案
  4. 询问确认 - 用户同意后执行修复
  5. 结果汇总 - 显示修复成功/失败

输出示例

🛡️ OpenClaw 安全扫描报告
📅 扫描时间: 2026-03-15 16:57
📊 安全评分: 25/100

📋 详细发现:

【1】[操作规则] 🟠 高危
问题: 未设置删除操作限制
详情: Agent 可能执行删除操作而不需要人工确认
🔧 可修复: 是

💡 发现 5 个可修复的问题,运行:
   python3 scripts/scan_security.py --interactive

交互式修复示例

【问题 1】未设置删除操作限制
风险等级: 🟠 高危

📝 修复方案:
  在文件中添加规则: 操作红线: 只能执行查询和修改,删除操作必须手动确认

是否执行此修复? (y/n/skip/all): y
✅ 已在 TOOLS.md 中添加操作红线规则

安全评分规则

  • 100 分起
  • 🔴 严重: -25 分
  • 🟠 高危: -15 分
  • 🟡 中危: -5 分
  • 🟢 低危: -2 分

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Security

Deepsafe Scan

Preflight security scanner for AI coding agents — scans deployment config, skills/MCP servers, memory/sessions, and AI agent config files (hooks injection) f...

Registry SourceRecently Updated
3590Profile unavailable
Security

AgentTrust — Security Scanner for AI Skills

Scan AI skills for malware, injections, data leaks, verify integrity, and check agent wallet reputation without API keys or accounts.

Registry SourceRecently Updated
1110Profile unavailable
Security

Skill Sentinel

Scan OpenClaw skill directories for high-signal security risks such as download-and-execute chains, obfuscated execution, and suspicious callbacks.

Registry SourceRecently Updated
1690Profile unavailable
Security

CrawSecure

Offline security scanner that detects unsafe code patterns in ClawHub skills before installation to help users assess potential risks locally.

Registry SourceRecently Updated
1.9K1Profile unavailable