CVE-2026-54233

Published: Jun 22, 2026Modified: Jun 24, 2026

6.5

Vector

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Exploitability: 2.8 / Impact: 3.6

Source: security-advisories@github.com (Secondary)

Description

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.

Affected (1)

Products: Vllm: Vllm

1 product

Configuration A

1 vulnerable

Vulnerable Software	Affected Versions
Vllm Vllm	Before 0.23.1

Related CWEs

Improper Handling of Highly Compressed Data (Data Amplification)

The product does not handle or incorrectly handles a compressed input with a very high compression ratio that produces a large output.

References (2)

https://github.com/vllm-project/vllm/pull/44970

Source: security-advisories@github.com

Issue TrackingPatch

https://github.com/vllm-project/vllm/security/advisories/GHSA-6pr9-rp53-2pmc

Source: security-advisories@github.com

Third Party Advisory

Timeline

No history available yet.