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.
Read at Cloudflare blog (security)
Why it ranks 4 (Routine)
- Threat research
- Recency: items published within 24 hours gain 15, within 72 hours 6, within 7 days 2.
Links
- Cloudflare blog (security) (blog.cloudflare.com)