← 返回 Skills 市场
577
总下载
0
收藏
4
当前安装
1
版本数
在 OpenClaw 中安装
/install browser-automation-1
功能描述
Automate web browsing tasks like navigation, data extraction, form filling, clicking, and screenshots using the agent-browser CLI.
使用说明 (SKILL.md)
Browser Automation
Automate web browser interactions using natural language via CLI commands.
When to Use
- Browse websites
- Navigate web pages
- Extract data from websites
- Take screenshots
- Fill forms
- Click buttons
- Interact with web applications
Tools
Uses agent-browser CLI for headless browser automation.
Capabilities
- Headless browser control
- Screenshot capture
- Form filling
- Button clicking
- Data extraction
- Navigation control
安全使用建议
This skill is internally inconsistent and requires caution. Before installing or running it: 1) Do not provide API keys or credentials until you confirm the skill's code and provenance — the docs reference ANTHROPIC_API_KEY but the skill metadata does not declare it. 2) Treat the .chrome-profile and ./agent/downloads/ behavior as persistent storage for cookies and files; if you run it, use an isolated/ephemeral environment or remove the profile directory afterward. 3) The bundle lacks source code and a trustworthy install method (setup.json asks you to npm install/link, but no package code is included) — ask the publisher for the full source, a verifiable homepage/repository, and a reproducible install manifest. 4) If you must test it, run in a sandboxed VM or container with no real credentials and no sensitive browser profiles, and monitor outbound network traffic (the tool appears to rely on an external AI model which may receive page content). 5) If you cannot verify origin or inspect the implementation, do not install or supply secrets; consider rejecting the skill until the author provides a complete, auditable package and clear declarations of required env vars and data flows.
功能分析
Type: OpenClaw Skill
Name: browser-automation-1
Version: 1.0.0
The skill bundle describes a browser automation tool with high-risk capabilities, including session persistence via local Chrome profiles, automatic file downloads, and data extraction. Several significant anomalies suggest the package is untrustworthy: it references a non-existent AI model version (`claude-haiku-4-5-20251001`), contains a future publication date (March 2026) in `_meta.json`, and lacks the actual implementation source code (`src/cli.ts`) and `package.json` required to verify its behavior. These discrepancies, combined with the requirement for an `ANTHROPIC_API_KEY` and the use of off-screen browser windows (`--window-position=-9999,-9999`), justify a suspicious classification.
能力评估
Purpose & Capability
The name/description (browser automation) matches the SKILL.md capabilities (navigate, extract, fill, screenshot). However the skill declares no required binaries or env vars while its docs and setup.json clearly expect a global 'browser' CLI, a local Chrome installation, Node.js dependencies, and an ANTHROPIC_API_KEY. That mismatch is disproportionate and unexplained.
Instruction Scope
The runtime instructions and examples instruct the agent to: launch Chrome with a persistent profile (.chrome-profile/), automatically download files to ./agent/downloads/, and perform authenticated logins (examples include filling passwords). The REFERENCE explicitly says AI model (Anthropic Claude Haiku) is used to interpret page actions — meaning page content and possibly credentials may be sent to an external model. The SKILL.md does not declare or limit this telemetry, so the instruction scope goes beyond simple local automation and may expose sensitive data.
Install Mechanism
There is no formal install spec in the skill bundle, yet setup.json instructs users to run npm install and npm link and to ensure a globally linked 'browser' command. The package files present (package-lock.json empty, no source files) suggest the implementation is missing from the bundle or the skill expects an out-of-band install step from an unknown source. That is incoherent and increases risk because installing arbitrary npm packages from an unknown origin is high-risk.
Credentials
The skill's declared requirements list no environment variables, but setup.json explicitly demands ANTHROPIC_API_KEY and the docs reference launching Chrome with a user-data-dir (persistent cookie/session storage). Requesting an external model API key and persisting browser profile data are high-privilege operations that are not proportional to the skill's explicit metadata and were not declared up front.
Persistence & Privilege
The skill does not set always: true and does not claim to modify other skills. However it preserves a Chrome profile (.chrome-profile/) and writes downloads/screenshots to agent directories, meaning it will persist session cookies, local storage, and any downloaded files across runs — a surprising persistence behavior that can leak credentials or session tokens if not expected.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install browser-automation-1 - 安装完成后,直接呼叫该 Skill 的名称或使用
/browser-automation-1触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of browser-automation-1
- Automate web browser interactions through the command line.
- Supports tasks like browsing, navigation, data extraction, form filling, clicking, and screenshots.
- Works with Chrome, Brave, and Edge browsers using the agent-browser CLI.
- Designed for headless browser control and seamless interaction with web applications.
元数据
常见问题
Browser Automation 1 是什么?
Automate web browsing tasks like navigation, data extraction, form filling, clicking, and screenshots using the agent-browser CLI. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 577 次。
如何安装 Browser Automation 1?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install browser-automation-1」即可一键安装,无需额外配置。
Browser Automation 1 是免费的吗?
是的,Browser Automation 1 完全免费(开源免费),可自由下载、安装和使用。
Browser Automation 1 支持哪些平台?
Browser Automation 1 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Browser Automation 1?
由 nuradil(@nuradil)开发并维护,当前版本 v1.0.0。
推荐 Skills