English(EN) Test shows how browser add-on could give commands to computer via Claude

Anthropic的Claude桌面版通过浏览器插件易受本地命令执行攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 14:06

研究人员演示了Anthropic的Claude桌面应用程序中的一个安全漏洞，该漏洞允许浏览器扩展利用Dispatch功能执行本地命令。该漏洞利用了Claude网站上的恶意脚本与Dispatch功能进行交互，该功能通常允许将任务从移动设备发送到桌面应用程序。虽然助手需要用户批准，但插件可以自动确认命令，从而在没有浏览器漏洞的情况下安装软件和执行应用程序。Anthropic承认了该问题，最初将其标记为重复项，但此后已停用Dispatch功能以解决此问题。 AI

影响凸显了AI助手与本地系统集成所带来的潜在风险以及对强大安全措施的需求。

排序理由在AI产品的特定功能中发现安全漏洞。

在 dev.to — Anthropic tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 28 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 在AI产品的特定功能中发现安全漏洞。
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: safety, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

dev.to — Anthropic tag TIER_1 English(EN) · Hacks.gr · 2026-11-06 14:06

Test shows how browser add-on could give commands to computer via Claude

<p>Researchers demonstrated how a browser extension with script access on could interact with Claude Desktop's Dispatch feature to execute code locally.</p> <p>The test was conducted by Forever Security and involved Dispatch, a feature of Claude that allows tasks to be sent from …

本文如何被排名

报道来源 [1]

Test shows how browser add-on could give commands to computer via Claude

相关实体

相关话题