# CVE-2026-109228: SGLang resource budget bypass in GLM-V video processing

Source: https://junglewise.ai/threats/cve-2026-109228-sglang-through-0-5-21-contains-a-resource-budget-bypass  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-10-12. Updated: 2026-10-16  
License: CC BY 4.0 with a link back

CVE-2026-109228 · Severity: high · CVSS 7.5 · Published 2026-10-12

SGLang is a serving framework for large language models and multimodal models. A resource budget bypass vulnerability allows remote attackers to force excessive video frame decoding by manipulating parameters, causing worker memory exhaustion and denying service to legitimate users.

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

## Quick answers

**Is CVE-2026-109228 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-109228 being exploited in the wild.

**How severe is CVE-2026-109228?** High severity, with a CVSS score of 7.5, published 12 October 2026.

**Which products and versions are affected?** SGLang Project SGLang through 0.5.21.

**Is there a fix for CVE-2026-109228?** 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-2026-109228 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-109228?** 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 exists in SGLang's GLM-V video processing component (glm4v.py), where insufficient validation of fps, max_frames, max_tokens_per_frame, and max_image_tokens parameters supplied in the video_url object allows attackers to set these values arbitrarily high. This causes the framework to decode every frame of high-resolution video at full resolution, exhausting available memory on worker nodes. The attack is network-accessible with no authentication required.

## Affected products

- SGLang Project SGLang through 0.5.21

## Timeline

- 2026-10-12: disclosed

## References

- [https://pypi.org/project/sglang](https://pypi.org/project/sglang)
- [https://github.com/sgl-project/sglang](https://github.com/sgl-project/sglang)

## 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 Mooncake disaggregation backend unauthenticated denial of service](https://junglewise.ai/threats/cve-2026-112269-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)