Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Cloudflare discloses GLM-5.3 cross-request data exposure

AI summary

Cloudflare said 155 responses from the GLM-5.3 model on Workers AI contained data from other customers’ requests between August 27 and September 9, 2026. The affected responses followed prompts longer than 681,280 tokens and resulted from a deployment mismatch combined with an SGLang bug involving rejected over-length prompts and stale KV cache state. Cloudflare remediated the issue and restored the model on September 9, and recommends that SGLang operators update to v0.5.22 or later.

In-depth insight

The incident exposed real tenant-isolation failures in a production AI serving stack, while the disclosed configuration and engine patches provide concrete guidance for other Workers AI and SGLang operators.

On September 8, 2026, we were alerted by a security researcher, Gadi Evron from Knostic, to a tenant isolation issue affecting the GLM-5.3 Workers AI model (@cf/zai-org/glm-5.3) starting on August 27, 2026. We have remediated the issue, and we restored the model on September 9. We have confirmed that no other model hosted on Workers AI was affected.

Between August 27 and September 9, a small number of customers using the GLM 5.3 Workers AI model received responses that contained data from other customers' requests made to the same model shortly before theirs. In total, 155 responses were affected, all to prompts longer than 681,280 tokens.

After excluding our own testing and the researcher's, the requests we identified are consistent in timing and volume with ordinary long-context use, not with someone repeatedly exploiting the bug. We found no evidence of deliberate exploitation.

Today we are publishing this report alongside a post from SGLang, the open-source inference engine that we use, as a coordinated disclosure.This post describes the bug that caused this issue, our response timeline, and the subsequent hardening we have conducted on our production SGLang deployments. We also detail our continued efforts with the upstream maintainers of SGLang to address this and similar bugs.

#Cloudflare#GLM-5.3#Workers AI#SGLang#Z.ai#Knostic

Original · 16 min readRead the original
Group chat

No comments yet. Start the conversation.