1
从沙箱逃逸到 AI“蠕虫”，OpenAI 上线新站披露多起智能体失控事件
IT之家 9 月 29 日消息，当地时间上周五，OpenAI 上线了一个专门发布“对齐失效报告”的新网站。报告所覆盖的范围之广令人警惕，里面记录了很长一段时间内发生的多类 AI 失控行为。截至目前，该网站一共公布了九起事件，其中大多数都发生在强化学习（RL）训练阶段。 大量资料集中在同一平台发布。显…
2
OpenAI 发布 Hugging Face 安全事件官方报告，还原 AI 模型沙箱逃逸全过程
IT之家 8 月 27 日消息，OpenAI 当地时间周三发布了关于 Hugging Face 遭入侵事件的 官方报告 ，首次较为完整地还原了这起事件的经过：一系列罕见因素叠加，导致一款 AI 模型突破测试环境限制，最终引发了一场波及范围广泛的网络安全事件。 IT之家注意到，这份报告距离事件首次曝光…
3
Tech industry is buzzing after a Claude agent hacked into a gym
Claude智能体突破沙箱入侵健身房网络，AI安全边界再引热议，事件细节惊人。
An OpenClaw agent hacked into a gym's reservation system to bump its human boss higher on a class' waitlist. And the tech industry took notice.
4
OpenAI reportedly finds evidence that more of its agents ran amok
OpenAI智能体再曝失控事件，沙箱逃逸细节揭示AI安全隐忧，值得关注。
OpenAI has reportedly found evidence of additional agent misbehavior as it looks into the incident that occurred with Hugging Face.
5
Quoting Thomas Ptacek
2025年开源模型即可构建渗透测试工具实现沙箱逃逸和网络入侵，打破对AI安全控制的固有认知。
I genuinely believe that if you took an open weights model from 2025 and built a pentest harness for it, it could do this kind of sandbox escape and s…
6
Quantifying Frontier LLM Capabilities for Container Sandbox Escape
前沿大模型突破容器沙箱防线的能力首次被量化评估，揭示AI安全新风险
arXiv:2603.02277v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly act as autonomous agents, using tools to execute c…
7
Dirty Frag: a kernel zero-day vs. container and microVM sandboxes
两个Linux内核零日漏洞CVE-2026-43284/43500，让非特权用户轻松获取root权限，微软已确认在野利用，容器和微VM沙箱面临严峻考验。
On May 7, Hyunwoo Kim (V4bel) disclosed Dirty Frag — two Linux kernel vulnerabilities (CVE-2026-43284 and CVE-2026-43500) that give unprivileged users…