CVE-2026-109225

SGLang through 0.5.21 Memory Exhaustion DoS via /v1/audio/transcriptions Upload

Published Oct 12, 2026 CVSS 4.0 · 8.7 High EPSS < 1% KEV · Not listed
Description
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.

Analysis

AI-generated

Technical impact

SGLang versions up to and including 0.5.21 contain an unbounded in‑memory allocation that processes every multipart upload to the /v1/audio/transcriptions endpoint before performing any validation. An unauthenticated remote attacker can send arbitrarily large or many concurrent files, causing the server to exhaust all available memory, crash the HTTP/tokenizer worker, and render the service unavailable. The flaw results in a denial of service but does not compromise confidentiality or integrity.

Affected Systems

The vulnerability affects installations of SGLang from the sgl‑project, specifically versions 0.5.21 and earlier. Any deployment that exposes the /v1/audio/transcriptions HTTP interface to external traffic is at risk. The flaw resides in the Python entry point and is independent of the underlying operating system.

Risk and Exploitability

The CVSS base of 8.7 indicates high severity. Exploitation requires only unauthenticated access to the exposed endpoint, and there is no built‑in mitigation. EPSS data is unavailable, and the vulnerability is not listed in CISA KEV, so while the exploitation likelihood is uncertain, the lack of a mitigated user base does not diminish the risk that a determined attacker can achieve a service outage.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade SGLang to the latest release that contains a fix for the memory exhaustion bug.
  • If an upgrade is not immediately feasible, restrict or filter access to the /v1/audio/transcriptions endpoint with firewall rules or a reverse proxy, and apply rate‑limiting or maximum request‑size limits to incoming uploads.
  • If the transcriptions feature is not required, disable or remove the /v1/audio/transcriptions endpoint from the deployment.
  • Configure the HTTP/tokenizer worker to restart automatically through a supervisor or container orchestration platform so that a crash causes an instant recovery.

Generated by OpenCVE AI on October 12, 2026 at 15:37 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'yes', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Sgl-project
Sgl-project sglang
Vendors & Products Sgl-project
Sgl-project sglang
Type Values Removed Values Added
Description 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.
Title SGLang through 0.5.21 Memory Exhaustion DoS via /v1/audio/transcriptions Upload
First Time appeared Lmsys
Lmsys sglang
Weaknesses CWE-770
CPEs cpe:2.3:a:lmsys:sglang:*:*:*:*:*:*:*:*
Vendors & Products Lmsys
Lmsys sglang
References
Metrics cvssV3_1

{'score': 7.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H'}

cvssV4_0

{'score': 8.7, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N'}

Weaknesses
  • CWE-770

    Allocation of Resources Without Limits or Throttling

Sources

Status
PUBLISHED
Assigner
VulnCheck
Published
Updated
Oct 13, 2026, 4:57 PM
Reserved
Oct 12, 2026, 1:46 PM
Status
Deferred
Published
Oct 12, 2026, 2:17 PM
Modified
Oct 13, 2026, 5:17 PM