Original post · AI translation
在 Epoch AI 的测试中，Z .ai 的开放权重模型 GLM 5.3 将尚未发布的 Firefox 安全修复转化为可用的攻击手段（即构建出了可用的漏洞利用代码），连续涉及 6 个版本。
这些修复在进入稳定版浏览器之前就已出现在公开代码中，并伪装成常规改动，以拖慢攻击者的脚步。
尽管任何提供商都没有作出过一次拒绝，GLM 5.3 仍自行找出了真正的补丁，并独立构建了完整的漏洞利用链。
最终得到的是一个网页：访问者无需进一步点击，它就能将访问者的本地文件发送给攻击者，也为获取已保存的密码和 Cookie 提供了一条途径。
研究人员起初花费超过 100,000 美元搭建了一个安全的测试系统，但此后每次额外攻破 Firefox 的成本只有约 1,000 美元，最快的一次耗时 12 小时。
每次攻击还利用了 Firefox 中另一个此前无人知晓的漏洞；AI 自行发现了该漏洞，Mozilla 于 10 月 27 日修复了它。
研究人员在 Google Chrome 上尝试了同样的方法，但即使花费了约 100,000 美元，仍未成功。
Original
In Epoch AI tests, Z .ai’s open-weight GLM 5.3 turned unshipped Firefox security fixes into working attacks (i.e. built working exploits) on 6 consecutive releases. Those fixes sit in public code before reaching the stable browser, disguised as routine changes to slow attackers. Without a single refusal from any provider, GLM 5.3 still picked out the real patches and built a full exploit chain alone. The result was a webpage that sent a visitor’s local file to the attacker with no further clicks, a route to stored passwords and cookies. The researchers first spent over $100K building a safe test system, but after that, each extra Firefox hack cost only about $1,000, and the fastest took 12 hours. Every hack also used a second Firefox bug that nobody knew about, which the AI found by itself and Mozilla fixed on October 27. The researchers tried the same thing on Google Chrome and failed, even after spending about $100K.