安全扫描
OpenClaw
可疑
medium confidence该技能的代码和指令与其所述目的(浏览器自动化V2)一致,它使用浏览器自动化技术进行交互,请求适当的配置,不请求无关的凭证或意外端点。
评估建议
此技能似乎确实做到了它声称的:浏览器自动化工具v2,用于高级网页交互和操作。安装或运行之前:1) 确认您对授予浏览器访问权限感到满意——该工具可以访问任何URL。2) 仅将其用于您有权访问的网站,避免访问受保护的内容,除非您完全信任设置。3) 技能不请求凭证,但注意不要向脚本传递敏感的URL或凭证,除非您信任整个工具链。4) 如果您想要更高的保证,请在运行前在本地审查包含的脚本。...详细分析 ▾
✓ 用途与能力
Name/description match the code: the files implement an OpenClaw CLI-driven browser manager and helpers (search, fetch, multi-page, form fill). No unrelated credentials or services are requested.
⚠ 指令范围
Runtime instructions and scripts call the OpenClaw CLI to control a browser (expected). However many commands are built by interpolating user-supplied data (URLs, JSON field values, refs) into shell command strings passed to exec — this can allow shell/command injection if inputs are untrusted. The SKILL.md suggests running the scripts directly and setting env vars but does not warn about sanitizing inputs.
✓ 安装机制
No install/download step; the skill is instruction+code only. Nothing is fetched from external URLs or installed automatically.
✓ 凭证需求
The skill declares no required secrets or config paths. It uses optional environment variables for profile/timeout/retries which are proportional to a browser automation tool.
✓ 持久化与权限
always is false, the skill doesn't request permanent platform-level presence or modify other skills. It writes lock files under /tmp for concurrency control (expected).
安全有层次,运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv2.0.02026/2/16
初始版本,支持浏览器自动化V2
● 可疑
安装命令 点击复制
官方npx clawhub@latest install browser-automation-v2
镜像加速npx clawhub@latest install browser-automation-v2 --registry https://cn.clawhub-mirror.com
技能文档
Enterprise-grade browser automation for OpenClaw with robust resource management.
Features
- ✅ Automatic 标签页 cleanup - 否 更多 标签页 accumulation
- ✅ 超时 & 重试 - Exponential backoff 在...上 network errors
- ✅ Smart waiting -
waitForLoadState,waitForSelector - ✅ Concurrency lock - Prevents 个人资料 conflicts
- ✅ Structured logging - DEBUG=1 对于 verbose 输出
- ✅ Configurable - Environment variables 对于 超时, retries, 个人资料
Files
browser-manager.v2.js- Core manager 类搜索-google.js- Google 搜索 带有 screenshot + PDF获取-summary.js- 获取 page content (static 或 dynamic)multi-pages.js- Batch process multiple URLsfill-表单.js- Auto-fill forms 由 字段 names
Usage
# Set environment (optional)
export BROWSER_PROFILE=openclaw
export BROWSER_TIMEOUT=30000
export BROWSER_RETRIES=2
export DEBUG=1cd ~/.openclaw/workspace/skills/browser-automation-v2
# Search Google
node search-google.js "OpenClaw automation"
# Batch process
node multi-pages.js "https://example.com" "https://github.com"
# Fill form
node fill-form.js "https://example.com/form" '{"email":"test@xx.com"}'
Integration
Register as OpenClaw skill:
openclaw skills install ~/.openclaw/workspace/skills/browser-automation-v2
Or call directly from agent:
run search-google.js "query"
Requirements
- OpenClaw v2026.2.15+
- Browser 个人资料 configured (默认:
openclaw) - Gateway running
Troubleshooting
- 超时 errors: Increase
BROWSER_TIMEOUT - 个人资料 locked: Wait 对于 其他 instance 到 finish
- 元素 不 found: 使用
snapshot --格式 ai到 debug refs
Created: 2026-02-16 Version: 2.0.0 License: MIT
数据来源:ClawHub ↗ · 中文优化:龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制
免费技能或插件可能存在安全风险,如需更匹配、更安全的方案,建议联系付费定制