Cloudflare discloses cross-customer data exposure in 155 AI responses

Cloudflare disclosed that 155 responses from its GLM-5.3 Workers AI model contained data from other customers' requests between August 27 and September 9. The company restored the model on September 9 after correcting its configuration and patching the inference engine. The model accepted a 1,048,576-token context window, but memory used to store processed prompts held only 681,280 tokens. A bug in the SGLang engine allowed rejected oversized requests to generate responses using memory left by earlier requests. Cloudflare says every affected response followed a prompt longer than 681,280 tokens. It found no evidence of deliberate exploitation and says no other Workers AI model was affected. The company recommends that other SGLang operators update to v0.5.22 or later.