# CVE-2026-109226: SGLang decompression amplification in load_audio

Source: https://junglewise.ai/threats/cve-2026-109226-sglang-through-0-5-21-contains-a-decompression-amplification  
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-2026-109226 · Severity: high · CVSS 7.5 · Published 2026-10-12

SGLang is a framework for serving large language models and multimodal models. A vulnerability in its audio loading function allows remote attackers to submit highly compressed audio files that expand into massive buffers, exhausting server memory and causing denial of service attacks that disrupt the service.

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

## Quick answers

**Is CVE-2026-109226 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-109226 being exploited in the wild.

**How severe is CVE-2026-109226?** 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-2026-109226?** 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-2026-109226 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-109226?** 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

A decompression amplification vulnerability in the load_audio function fails to enforce duration or sample limits when decoding FLAC-encoded audio. Attackers can supply small compressed audio files via audio_url or audio_data inputs that decompress into huge PCM buffers, consuming worker memory and CPU resources. The vulnerability requires network access and no authentication.

## 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)