---
id: CVE-2026-109225
title: >-
  SGLang through 0.5.21 contains an unbounded memory allocation vulnerability
  that allows unauthenticated remote attackers to exhaust memory by uploading
  oversized files to /v1/audio/transcriptions
summary: >-
  SGLang through 0.5.21 contains an unbounded memory allocation vulnerability
  that allows unauthenticated remote attackers to exhaust memory by uploading
  oversized files to /v1/audio/transcriptions. Attackers can send concurrent
  large mult…
severity: high
cvss: 7.5
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H'
cwe:
  - CWE-770
published: '2026-10-12'
updated: '2026-10-12'
sourceUpdated: '2026-10-12T14:17:11.700'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-109225'
references:
  - url: 'https://github.com/sgl-project/sglang'
    label: disclosure@vulncheck.com
  - url: >-
      https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/entrypoints/http_server.py#L1847-L1871
    label: disclosure@vulncheck.com
  - url: 'https://github.com/sgl-project/sglang/issues/43709'
    label: disclosure@vulncheck.com
  - url: >-
      https://www.vulncheck.com/advisories/sglang-through-0.5.21-memory-exhaustion-dos-via-v1-audio-transcriptions-upload
    label: disclosure@vulncheck.com
tags:
  - nvd
ingestedAt: '2026-10-12T14:50:34.121Z'
---

## Overview

SGLang through 0.5.21 contains an unbounded memory allocation vulnerability that allows unauthenticated remote attackers to exhaust memory by uploading oversized files to /v1/audio/transcriptions. Attackers can send concurrent large multipart uploads, which are fully read into memory before validation, to crash the HTTP/tokenizer worker and deny service.

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.