stuarthu/dsh-chrome
DeepSeek Harness (dsh) 浏览器伴侣:Chrome 侧边面板,嵌入完整的 dsh 网页界面,并附带主机插件,用于页面读取、HTTP 捕获和浏览器控制。
Project Overview项目介绍
This is a native plugin built exclusively for DeepSeek Harness (DSH), consisting of two core components: host plugins that run inside DSH and a Chrome extension that runs in the browser. It embeds the full DSH web UI into a Chrome side panel, enabling the DSH agent to automatically detect the current open page, read its content, capture HTTP traffic, and perform browser actions like navigation, clicking, and opening new tabs. It relies on explicit user intent from the user’s prompt to unlock state-changing browser actions, preventing unwanted manipulation of the browser by hidden instructions on web pages.
Installation has two required steps: first, add the host plugin to your DSH web profile via the DSH CLI command dsh plugin --profile web add dsh-chrome, which registers the bridge, browser tools, and page injector automatically. Next, run npx dsh-chrome install to copy the Chrome extension files to a stable per-user directory, then open Chrome’s extension page, enable developer mode, and load the unpacked extension from the printed directory. Once installed, you can open the dsh-chrome side panel from the Chrome toolbar and use DSH normally to automate browser tasks with natural language.
This plugin requires DSH web to be running locally on your local machine (default address is http://127.0.0.1:3080, configurable in the extension settings) and Chrome 118 or newer to work correctly. It is released under the open source MIT license, so it is completely free to use, modify, and distribute per the license terms. There are a few key limits: only http(s) pages are automatically injected, the extension’s top-bar UI is currently Chinese only, captured traffic does not include HTTP headers, and all credentials are redacted by default for user security.
这是DeepSeek Harness的原生插件,由DSH端的宿主插件和Chrome浏览器扩展两部分组成,它在Chrome侧边栏嵌入完整的DSH Web界面,让DSH代理能够自动感知当前浏览页面内容、捕获HTTP请求、操控浏览器动作,帮助DSH实现完整的浏览器自动化交互能力。
安装需要先通过DSH CLI将宿主插件添加到DSH Web配置,再通过npx命令安装扩展文件,之后在Chrome的扩展管理页面开启开发者模式,加载解压后的扩展。用户打开Chrome侧边栏的DSH界面后,就可以通过自然语言指令让代理完成打开页面、点击元素、抓包等操作。
该插件要求本地运行DSH Web服务,并且Chrome版本不低于118,遵循MIT许可协议免费开源。扩展UI顶栏仅支持中文,嵌入的DSH界面遵循DSH本身的语言设置,浏览器仅对http(s)页面自动注入内容,受限页面会通过远程调试协议访问,捕获请求中的敏感信息默认脱敏处理。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:dsh-chrome(stuarthu/dsh-chrome)
仓库:https://github.com/stuarthu/dsh-chrome
本站详情页:https://www.yhbd.top/plugins/stuarthu-dsh-chrome/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 9 · 最近提交 2026-08-22 · 主语言 JavaScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- Only 9 stars - very few users, little community feedback星标只有 9,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add dsh-chrome
把 stuarthu/dsh-chrome 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
dsh-chrome — DeepSeek Harness browser companion
English | 中文
A Chrome side panel that embeds the full dsh web UI (sessions, settings, approvals, tasks, goals, workspaces — everything) and lets the dsh agent perceive and drive your browser:
- Sees the current page automatically. After you switch tabs or navigate
(SPA routes included), the "current page" (URL, title, body text, capped at
1,000,000 characters) is injected into your most recently active session, so
the agent knows what you are looking at. Only
http(s)tabs are injected this way. - Reads HTTP traffic on request. When you ask it to, the agent starts a
capture (
browser_start_capture) and records the active tab's request method, URL, status, request body and response body via the Chrome DevTools Protocol;browser_capture_requestsreads them back. Secret-shaped values are masked by default — see Security. - Drives the browser.
browser_navigate/browser_click/browser_open_tab. - Approval-free, with tool-level intent unlock. State-changing actions run
only when the current turn was started by a real message from you that
contains explicit browser intent. The words that unlock
browser_navigate/browser_click/browser_open_tabare open, navigate, click, visit, tab (打开 / 跳转 / 前往 / 点击 / 导航 / 访问 / 浏览一下 / 新标签), plus "go to" when it is followed by a page or URL (go to github.com,go to the page— a barego to the next stepdoes not unlock anything); the words that unlockbrowser_start_captureare capture, debug (抓包 / 抓一下 / 抓取请求 / 监听网络 / 网络请求 / 流量). Note that 抓取 on its own does not unlock capture — it reads as ordinary "fetch/scrape" intent; say 抓包 or 抓取请求. If an action is blocked you get a refusal quoting the exact words that would unlock that tool, so you can simply restate. An instruction hidden inside a web page cannot drive the browser (best-effort protection in approval-free mode, not an absolute guarantee). - While capturing, Chrome shows a "debugging this browser" banner (it disappears when capture stops).
Prerequisites
dsh webrunning locally (defaulthttp://127.0.0.1:3080; configurable in the extension's settings).- Chrome 118+ (the extension relies on
InjectionResult.error, added in Chrome 118).
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
Tencent/BrowserSkill
YaoApp/yao
anbeime/skill
Jesseovo/last30days-skill-cn
bowenliang123/dsh-context
platonai/Browser4
liustack/modsearch