CVE-2026-3059: Critical severity Lmsys Sglang vulnerability

Published Mar 12, 2026
·
Updated

SGLang's multimodal generation module is vulnerable to unauthenticated remote code execution through the ZMQ broker, which deserializes untrusted data using pickle.loads() without authentication.

Affected Software

2 affected components
pip/sglang<=0.5.9
Lmsys Sglang>=0.5.5<=0.5.9

Event History

Mar 12, 2026
CVE Published
via MITRE·11:37 AM
Data Sourced
via MITRE·11:37 AM
DescriptionWeakness
Data Sourced
via NVD·12:15 PM
DescriptionSeverityWeakness
Data Sourced
via NVD·12:15 PM
Affected Software
Advisory Published
via GitHub·12:30 PM
Data Sourced
via GitHub·12:30 PM
DescriptionSeverityWeaknessAffected Software

Frequently Asked Questions

1

What is the severity of CVE-2026-3059?

CVE-2026-3059 has a high severity rating due to the potential for unauthenticated remote code execution.

2

How do I fix CVE-2026-3059?

To fix CVE-2026-3059, update the SGLang package to a version higher than 0.5.9 that addresses this vulnerability.

3

What types of systems are affected by CVE-2026-3059?

CVE-2026-3059 affects systems using SGLang versions up to and including 0.5.9 that utilize the multimodal generation module with ZMQ.

4

What are the potential impacts of CVE-2026-3059?

The potential impacts of CVE-2026-3059 include unauthorized access and execution of malicious code on affected systems.

5

Is authentication required to exploit CVE-2026-3059?

No, CVE-2026-3059 can be exploited without any form of authentication, making it particularly concerning.

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