CVE-2026-54233
Medium
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.
SeverityMedium
CVSS6.5
Exploit probability—
ProductVllm
PublishedJun 22, 2026
First seenJun 22, 2026
Weakness typeCWE-409CWE-409
How to fix
Update
- vllm vllm0.23.1 or later
- vllm0.24.0 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| vllm vllm | v < 0.23.1 | 0.23.1 |
| vllmPyPI | v < 0.24.0, v ≤ 0.23.0 | 0.24.0 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
In the Intelligence 360 plan
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.