On September 8, 2026, Cloudflare was alerted by security researcher Gadi Evron (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. Cloudflare remediated the issue and restored the model on September 9. No other Workers AI model 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.
The report was the result of two overlapping issues: a misconfiguration where the KV cache pool (681,280 tokens) was smaller than the 1,048,576-token context window, and a SGLang bug in disaggregated prefill/decode mode where over-length requests were replaced with a one-token placeholder but still transferred stale KV pages to decode nodes.
Remediation included enlarging the prefill KV pool to ~2.04M tokens and patching the engine so rejected requests are retired before bootstrap or KV transfer. Cloudflare recommends all SGLang operators update to v0.5.22 or later.