Event ·Multi-source

黑客将 Claude 和 Grok 改造成自主攻击金融机构的智能体网络

网络安全研究显示，黑客把 Anthropic 的 Claude 和 xAI 的 Grok 组成 AI 智能体网络，自主攻击了超过 400 家金融机构等金融目标。研究已分享给 The Information。这是首次有公开报道显示消费级模型被大规模编排为自主攻击工具。

Current read

黑客把 Claude 和 Grok 拼成智能体网络，自己跑去攻击 400 多家金融机构，细节值得看看

11 sources76° AI heatLast updated 2026/10/22 13:00:20

Evidence

11 sources

Primary sourceThe Information

2026/10/22 13:00:20View source

Related source 1Andrew Curran

2026/10/20 16:27:07View source

Related source 2rohanpaul_ai

2026/10/21 19:48:33View source

Related source 3Teortaxes

2026/10/22 00:39:17View source

Related source 4kimmonismus

2026/10/20 14:17:05View source

Related source 5@cb_doge

2026/10/20 14:18:03View source

Related source 6IT之家

2026/10/21 01:14:34View source

Related source 7swyx (AI Engineer)

2026/10/21 05:06:02View source

Related source 8Gorden Sun

2026/10/21 23:36:20View source

Related source 9TestingCatalog

2026/10/22 08:23:08View source

Related source 10Decoder

2026/10/22 08:35:22View 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