CVE-2026-109228
SGLang through 0.5.21 Resource Budget Bypass via GLM-V Video Parameters
Description
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, max_frames, max_tokens_per_frame and max_image_tokens in the video_url 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.
INFO
Published Date :
Oct. 12, 2026, 2:17 p.m.
Last Modified :
Oct. 12, 2026, 2:17 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 3.1 | HIGH | [email protected] | ||||
| CVSS 4.0 | HIGH | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 4.0 | HIGH | [email protected] |
Solution
- Update SGLang to a version later than 0.5.21.
- Implement input validation for video processing parameters.
- Enforce strict limits on video processing resources.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-109228.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-109228 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-109228
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-109228 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-109228 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
New CVE Received by [email protected]
Oct. 12, 2026
Action Type Old Value New Value Added Description 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, max_frames, max_tokens_per_frame and max_image_tokens in the video_url 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. Added CVSS V4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H Added CWE CWE-770 Added Affected New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/109xxx/CVE-2026-109228.json">CVE-2026-109228</a> Added Reference https://github.com/sgl-project/sglang Added Reference https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/entrypoints/openai/protocol.py#L592-L594 Added Reference https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/multimodal/processors/glm4v.py#L160-L167 Added Reference https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/multimodal/processors/glm4v.py#L400 Added Reference https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/parser/conversation.py#L691 Added Reference https://github.com/sgl-project/sglang/issues/43705 Added Reference https://www.vulncheck.com/advisories/sglang-through-0.5.21-resource-budget-bypass-via-glm-v-video-parameters