CVE-2026-112269: SGLang through 0.5.22 Memory Exhaustion via Unauthenticated Mooncake Decode Registrations

Published Oct 19, 2026
·
Updated

SGLang through 0.5.22 with the Mooncake disaggregation backend accepts unauthenticated decode registration messages on the Prefill rank ZMQ PULL socket, allowing denial of service. Network-adjacent attackers can send many registrations with unique mooncakesessionid values and large nested-buffer frames to exhaust Prefill memory until the scheduler is OOM-killed.

Affected Software

1 affected component
SGLang SGLang<=0.5.22

Event History

Oct 19, 2026
CVE Published
via MITRE·01:55 PM
Data Sourced
via MITRE·01:55 PM
DescriptionSeverityWeakness
Data Sourced
via NVD·02:17 PM
DescriptionSeverityWeakness

Frequently Asked Questions

1

Which deployments are exposed?

SGLang deployments through 0.5.22 that use the Mooncake disaggregation backend are exposed when an attacker can reach the Prefill rank ZMQ PULL socket over an adjacent network.

2

What does an attacker need to exploit this issue?

No authentication or user interaction is required. An attacker needs network access to send decode registration messages to the Prefill rank socket, using many unique mooncake_session_id values and large nested-buffer frames.

3

What is the operational impact?

The registrations can exhaust memory on the Prefill process until the scheduler is killed by an out-of-memory condition, causing denial of service.

4

What can be done if patching is not immediately possible?

Restrict network access to the Prefill rank ZMQ PULL socket so untrusted adjacent-network systems cannot send decode registration messages.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203