Event ·Multi-source

美国初创公司 Cathedral 用智能体侵入 Anthropic 系统

美国初创公司 Cathedral 用 AI 智能体测试 Anthropic 的系统安全，在不到 12 小时内找到了访问其数据的路径。这次测试暴露了 AI 公司内部系统的安全漏洞。事件引发业界对 AI 公司自身安全防护能力的担忧。

Current read

一家叫 Cathedral 的美国公司用智能体不到 12 小时就摸进 Anthropic 的数据系统，AI 公司自己也不安全啊。

11 sources47° AI heatLast updated 2026/10/30 01:24:06

Evidence

11 sources

Primary sourceVnExpress Số hóa

2026/10/30 01:24:06View source

Related source 1VTV Công nghệ

2026/10/29 21:44:00View source

Related source 2Tech in Asia

2026/10/28 02:00:15View source

Related source 3Decoder

2026/10/28 10:56:24View source

Related source 4CNBC Indonesia Tech

2026/10/28 03:50:00View source

Related source 5IT之家

2026/10/28 23:05:14View source

Related source 6kimmonismus

2026/10/28 02:23:00View source

Related source 7Yuchen Jin

2026/10/28 02:35:14View source

Related source 8The Information

2026/10/28 18:30:06View source

Related source 9AIGCLINK

2026/10/28 03:20:14View source

Related source 10Anthropic: Research

2026/10/28 06:09:35View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story