Menu
OpenClaw扩展安全管理系统。扫描已安装扩展的安全风险，提供allowlist策略控制，在使用高风险扩展前进行风险提示。适用于安全管理、风险评估、权限控制场景。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Normalize palette and formatting in local image assets.
Remove hidden metadata from local SVG files for safer reuse.
Optimize local SVG files while staying inside the current image task.
Download and install skills from ClawHub (https://clawhub.ai). Use when user wants to browse, search, or download skills from the ClawHub skill registry.
Use this skill when users need help finding, discovering, or selecting OpenClaw skills from the Clawhub marketplace. Triggers include: '哪个技能适合', '怎么找到', '技能搜索', 'skill search', 'how to find skill', or any request about navigating the 238+ skill ecosystem. Helps users match their tasks to appropriate skills and understand skill capabilities.
Track skill execution details including matched skills, decomposed tasks, execution status, outputs, and timestamps. Called at the start of every conversation turn to record skill usage.
| name | skill-shield |
| description | OpenClaw扩展安全管理系统。扫描已安装扩展的安全风险，提供allowlist策略控制，在使用高风险扩展前进行风险提示。适用于安全管理、风险评估、权限控制场景。 |
| metadata | {"openclaw":{"emoji":"🛡️","requires":{"bins":["python3"]}}} |
安全管理已安装的OpenClaw扩展，扫描风险、存储风险列表、提供allowlist策略控制，确保在使用高风险扩展前进行风险提示和用户确认。
| 风险ID | 风险名称 | 严重程度 | 检测关键词 |
|---|---|---|---|
| R001 | 网络访问 | 高 | requests, curl, fetch, urllib, http, socket |
| R002 | 文件写入 | 高 | write, create, save, mkdir, rmdir, unlink |
| R003 | 文件读取 | 中 | read, open, cat, glob, listdir |
| R004 | 命令执行 | 严重 | exec, subprocess, shell, spawn, Popen, system |
| R005 | 外部API | 中 | api, webhook, endpoint, send, notify, post, get |
| R006 | 数据外发 | 严重 | upload, send, transfer, export, forward |
| R007 | 凭证访问 | 严重 | apiKey, password, token, secret, credential, auth |
| R008 | 无签名验证 | 低 | 无_meta.json文件 |
| R009 | 依赖未知 | 中 | requirements.txt, package.json, dependencies |
| R010 | 权限过宽 | 高 | chmod 777, allowlist, full |
执行skill-shield扫描所有已安装的扩展
执行skill-shield检查<extension-name>的风险
执行skill-shield添加<extension-name>到allowlist
执行skill-shield移除<extension-name>从allowlist
执行skill-shield添加<extension-name>到黑名单
执行skill-shield查看风险列表
执行skill-shield清除风险记录
配置文件位置：~/.openclaw/workspace/skills/skill-shield/config.json
{
"allowlist": ["file-search", "weather-search"],
"autoApprove": [],
"blocked": [],
"scanOnInstall": true,
"promptOnHighRisk": true
}
风险数据库位置：~/.openclaw/workspace/memory/shield-risks.json
{
"version": "1.0.0",
"lastScanTime": "2026-03-11T09:45:00Z",
"skills": {
"extension-name": {
"path": "/path/to/extension",
"risks": ["R001", "R004", "R006"],
"severity": "severe",
"scanTime": "2026-03-11T09:45:00Z",
"userDecision": "approved"
}
},
"allowlist": ["file-search", "weather-search"],
"history": [
{
"extension": "extension-name",
"action": "blocked",
"time": "2026-03-11T09:50:00Z"
}
]
}
用户：扫描所有扩展
Agent：🔍 正在扫描9个扩展...
📊 扫描完成!
🔴 严重: 6
🟠 高危: 1
🟡 中危: 0
🟢 低危/安全: 2
💾 风险报告已保存
用户：执行a-stock-dragon-tiger
Agent：⚠️ 安全警告
扩展: a-stock-dragon-tiger
风险等级: severe
风险项:
- R001: 网络访问
- R004: 命令执行
- R006: 数据外发
是否继续? (yes/no):
用户：yes
Agent：✅ 继续执行
用户：将weather-search添加到allowlist
Agent：✅ 已将weather-search添加到allowlist
后续使用将不再提示风险
| 严重程度 | 包含风险 | 用户确认要求 |
|---|---|---|
| 严重 | R004, R006, R007 | 强制确认 |
| 高 | R001, R002, R010 | 强制确认 |
| 中 | R003, R005, R009 | 建议确认 |
| 低 | R008 | 可选确认 |
~/.openclaw/workspace/skills/目录# 检查扩展目录权限
ls -la ~/.openclaw/workspace/skills/
# 手动运行扫描
python3 ~/.openclaw/workspace/skills/skill-shield/scripts/shield.py scan
# 重置配置文件
echo '{}' > ~/.openclaw/workspace/skills/skill-shield/config.json