Skip to content
Live
Trending storyPast story

Z.ai GLM-5.3 Workers AI model cache exposure

1 reports1 outlets23 days agoUpdate

The story so far

AI overview

The Z.ai GLM-5.3 Workers AI model caused 155 responses to leak other users' data due to incorrect SGLang inference engine configuration and bugs, involving requests with token lengths exceeding 681,280. Cloudflare fixed the issue and restored service on September 8, 2026, by adjusting the configuration and releasing an SGLang patch to resolve the vulnerability.

AI-written from the reports · Updated 20 days ago

Coverage timeline

Follow the coverage to see every side of the story.

27 Oct
  1. Hacker News · AI hot posts
    Cross-request KV cache exposure in the GLM-5.3 Workers AI model (155 responses)

    The Z.ai GLM-5.3 Workers AI model caused 155 responses to leak other users' data due to incorrect SGLang inference engine configuration and bugs, involving requests with token lengths exceeding 681,280. Cloudflare fixed the issue and restored service on September 8, 2026, by adjusting the configuration and releasing an SGLang patch to resolve the vulnerability.