Epoch AI 测试：智谱 GLM 5.3 连续 6 个版本将未发布的 Firefox 安全修复变成可用攻击
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 relea
Epoch AI 的测试中，智谱开源权重模型 GLM 5.3 连续 6 个 Firefox 版本把尚未进入稳定版的公开安全修复识别为真实补丁，并独立构建出完整攻击链，全程没有出现拒绝。最终生成的网页无需额外点击即可把访客本地文件发送给攻击者，并可触及已保存的密码和 Cookie。研究团队先投入超过 10 万美元搭建安全测试系统，此后每次攻击成本约 1000 美元，最快一次耗时 12 小时；每次攻击还用到 AI 自行发现的第二个未知 Firefox 漏洞，Mozilla 已于 10 月 27 日修复。对 Google Chrome 的同类尝试即使花费约 10 万美元也未成功。
正文
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.