CVE-2026-109228: SGLang through 0.5.21 Resource Budget Bypass via GLM-V Video Parameters

Published Oct 12, 2026
·
Updated

SGLang through 0.5.21 contains a resource budget bypass vulnerability that allows remote attackers to override GLM-V video processing limits by supplying fps, maxframes, maxtokensperframe and maximagetokens in the videourl object. Attackers can set these values arbitrarily high so glm4v.py decodes every frame of high-resolution video at full size, exhausting worker memory and denying service.

Affected Software

1 affected component
SGLang SGLang<=0.5.21

Event History

Oct 12, 2026
CVE Published
via MITRE·02:04 PM
Data Sourced
via MITRE·02:04 PM
DescriptionSeverityWeakness
Data Sourced
via NVD·02:17 PM
DescriptionSeverityWeakness

Frequently Asked Questions

1

Who can exploit this issue?

A remote attacker can exploit it without authentication or user interaction, provided they can submit a request containing a GLM-V video_url object to the affected SGLang service.

2

What request values are involved in the bypass?

The bypass uses fps, max_frames, max_tokens_per_frame, and max_image_tokens supplied in the video_url object. These values can be set arbitrarily high, overriding video-processing resource limits.

3

What is the practical impact on an affected worker?

The worker may decode every frame of a high-resolution video at full size. This can exhaust worker memory and cause denial of service.

4

Which versions are identified as affected?

SGLang through version 0.5.21 is identified as affected.

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