Cross-request KV cache exposure in the GLM-5.3 Workers AI model, and our remediation with SGLang
A configuration mismatch in GLM 5.3 on Workers AI triggered an SGLang bug that exposed KV cache pages across requests. Here is how we addressed the issue.
在 Cloudflare Blog (Security) 阅读
在 X 上接收快讯漏洞利用、重大泄露和故障,附应对措施。
关注 @vulnpulse_app检查你的信息是否已泄露
- Have I Been Pwned:免费查询你的邮箱地址是否出现在过去的泄露数据中(FBI 也提供泄露的密码)
- Google 密码检查:检查保存在 Google 中的密码是否泄露、重复使用或强度不足,并建议更改
| 来源 | Cloudflare Blog (Security) |
|---|---|
| 获取时间 | 2026/10/29 14:31 |
| 数据 | Markdown JSON |
2026/10/27 07:01,Cloudflare Blog (Security) 发布了“Cross-request KV cache exposure in the GLM-5.3 Workers AI model, and our remediation with SGLang”(类型:安全新闻)。相关技术:Cloudflare。