CVE-2026-54233

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to ~14.9GB of float32 PCM at decode time. This vulnerability is fixed in 0.23.1rc0.
Configurations

Configuration 1 (hide)

cpe:2.3:a:vllm:vllm:*:-:*:*:*:*:*:*

History

24 Jun 2026, 16:52

Type Values Removed Values Added
CPE cpe:2.3:a:vllm:vllm:*:-:*:*:*:*:*:*
First Time Vllm
Vllm vllm
References () https://github.com/vllm-project/vllm/pull/44970 - () https://github.com/vllm-project/vllm/pull/44970 - Issue Tracking, Patch
References () https://github.com/vllm-project/vllm/security/advisories/GHSA-6pr9-rp53-2pmc - () https://github.com/vllm-project/vllm/security/advisories/GHSA-6pr9-rp53-2pmc - Third Party Advisory

22 Jun 2026, 23:16

Type Values Removed Values Added
New CVE

Information

Published : 2026-06-22 23:16

Updated : 2026-06-24 16:52


NVD link : CVE-2026-54233

Mitre link : CVE-2026-54233

CVE.ORG link : CVE-2026-54233


JSON object : View

Products Affected

vllm

  • vllm
CWE
CWE-409

Improper Handling of Highly Compressed Data (Data Amplification)