经 AI Skill Hub 精选评估,AI代理浏览器防护 获评「推荐使用」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
浏览器扩展,提供30+规则,确保AI代理在浏览时安全
AI代理浏览器防护 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
浏览器扩展,提供30+规则,确保AI代理在浏览时安全
AI代理浏览器防护 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:npm 全局安装 npm install -g agent-browser-shield # 方式二:npx 直接运行(无需安装) npx agent-browser-shield --help # 方式三:项目依赖安装 npm install agent-browser-shield # 方式四:从源码运行 git clone https://github.com/pixiebrix/agent-browser-shield cd agent-browser-shield npm install npm start
# 命令行使用
agent-browser-shield --help
# 基本用法
agent-browser-shield [options] <input>
# Node.js 代码中使用
const agent_browser_shield = require('agent-browser-shield');
const result = await agent_browser_shield.run(options);
console.log(result);
# agent-browser-shield 配置说明 # 查看配置选项 agent-browser-shield --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export AGENT_BROWSER_SHIELD_CONFIG="/path/to/config.yml"
Alpha prototype: rulesets may change without notice
Agent Browser Shield is a Chromium extension for making agentic browser-use more effective and secure:
- Token efficiency: strip page chrome (footers, cookie banners, chat widgets, sponsored content) so agents spend tokens on the user's task. - Security & compliance: mask PII and credentials before they reach the model, and suppress hidden text, HTML comments, and user-generated content that could carry prompt-injection payloads. - Accuracy: block manipulative dark patterns and hide engagement rails and other content that could distract the model from the user's task.
Install from the Chrome Web Store — works on any Chromium-based browser (Chrome, Edge, Brave, Arc, Opera). For agent runtimes that need an unpacked extension or a ZIP, see the install guide.
Documentation — install guide, rule reference, and configuration.
Live demo site — RiverMart, a mock e-commerce SPA that exercises every rule. Load it with and without the extension to see the before/after difference.
ClawHub skill — for skill-aware OpenClaw agents, install with clawhub install agent-browser-shield to load the install paths and runtime behavior contract.

| Before | After |
|---|---|
|  |  |
- Node ≥ 24 and Bun ≥ 1.3 — extension and demo site - uv — runs the Python scripts (each declares its own PEP 723 deps; the repo pins Python 3.14 via .python-version, but scripts work on 3.11+) - Chrome / Chromium 148+ — to load the unpacked extension
uv run scripts/agent_task.py --with-extension \ --instruction "Find the top story on HN" ```
cd extension
bun install
bun run build
Which rules ship on by default is enumerated in extension/data/rule-defaults.json. To ship a build with a custom set without forking the repo, pass an override file to bun run build. The file is a flat JSON object whose keys are rule ids (same keys the Options-page export uses) plus a small set of reserved non-rule keys — currently optionsButton (boolean, default off) to enable the floating on-page button that opens the options page:
```sh bun run build --defaults ./my-defaults.json
cd extension && bun run build && bun run package && cd ..
demo-site/ is a Vite/React mock e-commerce SPA ("RiverMart") that deliberately packs the threats and dark patterns agent-browser-shield defends against onto a few pages. Load it with and without the extension to see the before/after difference.
Live deployment: <https://shield-dark-pattern-demo.vercel.app/>
To run it locally instead:
cd demo-site
bun install
bun run dev # http://localhost:5173
See demo-site/README.md for the per-page rule coverage and Vercel deploy instructions.
The Chromium MV3 extension lives in extension/. Build output goes to extension/dist/, which is what you load as an unpacked extension at chrome://extensions.
Bundle extension/dist/ into a ZIP suitable for uploading via the Browserbase extensions API:
```sh cd extension bun run build bun run package # writes output/agent-browser-shield-extension.zip at the repo root
uv run scripts/agent_task.py --instruction "Find the top story on HN"
该项目提供了一个开源的AI工作流,用于保护AI代理在浏览时的安全,规则数量多,但具体功能和效果需要进一步评估
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
AI Skill Hub 点评:AI代理浏览器防护 的核心功能完整,质量良好。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | agent-browser-shield |
| 原始描述 | 开源AI工作流:Browser extension with 30+ rules for keeping your AI agent safe while browsing。⭐11 · TypeScript |
| Topics | workflowai-agentsbrowser-extensionsecurity |
| GitHub | https://github.com/pixiebrix/agent-browser-shield |
| License | NOASSERTION |
| 语言 | TypeScript |
收录时间:2026-06-05 · 更新时间:2026-06-05 · License:NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端