# CVE-2026-112269: SGLang Mooncake disaggregation backend unauthenticated denial of service

Source: https://junglewise.ai/threats/cve-2026-112269-sglang-through-0-5-22-with-the-mooncake-disaggregation-backend  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-10-19. Updated: 2026-10-19  
License: CC BY 4.0 with a link back

CVE-2026-112269 · Severity: medium · CVSS 6.5 · Published 2026-10-19

SGLang is a framework for serving large language models. The Mooncake disaggregation backend (used to distribute inference workloads across multiple machines) accepts unauthenticated registration messages without validation, allowing an attacker on the same network to cause the prefill scheduler to run out of memory and crash by sending many malicious registration messages with large data payloads.

Technologies: [SGLang Project SGLang](https://junglewise.ai/threats/technologies/sglang). Vendors: [SGLang Project](https://junglewise.ai/threats/vendors/sglang-project).

## Quick answers

**Is CVE-2026-112269 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-112269 being exploited in the wild.

**How severe is CVE-2026-112269?** Medium severity, with a CVSS score of 6.5, published 19 October 2026.

**Which products and versions are affected?** SGLang Project SGLang through 0.5.22.

**Is there a fix for CVE-2026-112269?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-112269 attacked?** It is attacked from the adjacent network, in a software library.

**Am I affected by CVE-2026-112269?** Check whether you run SGLang Project SGLang at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

The vulnerability is an unauthenticated message acceptance flaw in the Prefill rank's ZMQ PULL socket handling of decode registration messages. The Mooncake backend fails to validate or limit incoming decode registration messages on the Prefill rank, allowing network-adjacent attackers to send registrations with unique session IDs and large nested-buffer frames. This causes memory exhaustion and out-of-memory (OOM) conditions in the prefill scheduler process.

## Affected products

- SGLang Project SGLang through 0.5.22

## Timeline

- 2026-10-19: disclosed

## References

- [https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/disaggregation/common/utils.py](https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/disaggregation/common/utils.py)
- [https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/disaggregation/mooncake/conn.py](https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/disaggregation/mooncake/conn.py)

## Related threats

- [SGLang uncontrolled memory allocation in Mooncake disaggregation backend](https://junglewise.ai/threats/cve-2026-112270-sglang-through-0-5-22-with-the-mooncake-disaggregation-backend)
- [SGLang server-side request forgery in prefill/decode disaggregation](https://junglewise.ai/threats/cve-2026-112267-sglang-through-0-5-22-in-prefill-decode-disaggregation-mode)
- [SGLang cache poisoning via untrusted mm_hashes in multimodal prefix cache](https://junglewise.ai/threats/cve-2026-111392-sglang-through-0-5-21-trusts-caller-supplied-mm-hashes-values-as)
- [SGLang code injection in _evaluate_filter()](https://junglewise.ai/threats/cve-2026-111391-sglang-0-5-10-through-0-5-22-contains-a-code-injection)
- [SGLang denial of service via disabled image decompression protection](https://junglewise.ai/threats/cve-2026-109229-sglang-through-0-5-21-contains-a-denial-of-service-vulnerability)