Event ·Multi-source

OpenAI 智能体发现至少 10 种全新 Linux 漏洞利用技术

OpenAI 发布消息称，其智能体在测试中发现并使用了至少 10 种 Linux 漏洞利用技术，经其咨询的专家确认均为此前未公开记录的新方法。这表明前沿 LLM 的能力已超出套用已知攻击手法，可以自行探索新的漏洞利用路径。消息同时提到这些智能体能够发现并修补新的利用方式。

Current read

OpenAI 说他们的智能体搞出了 10 种没人见过的 Linux 漏洞利用新招，安全圈可以看看细节。

11 sources79° AI heatLast updated 2026/11/4 23:13:26

Evidence

11 sources

Primary sourceOpenAI

2026/11/4 23:13:26View source

Related source 1IT之家

2026/11/4 09:11:48View source

Related source 2rohanpaul_ai

2026/11/3 00:36:40View source

Related source 3Tech in Asia

2026/11/3 02:59:27View source

Related source 4TestingCatalog

2026/11/3 07:41:31View source

Related source 5Decoder

2026/11/3 10:42:44View source

Related source 6The Information

2026/11/3 19:30:06View source

Related source 7Andrew Curran

2026/11/3 22:02:31View source

Related source 8AI Will

2026/11/4 07:04:24View source

Related source 9Gorden Sun

2026/11/4 15:50:57View source

Related source 10@atomic_chat_hq

2026/11/4 17:53:37View 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