CVE-2026-54233 | BDVDB-2026-342108 Detail
vllm-projectvllm
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.
Impact#
Per CVSS v3.1: confidentiality impact none, integrity impact none, availability impact high. Attack vector: network.
Weaknesses#
- CWE-409 Improper Handling of Highly Compressed Data (Data Amplification)
References#
Exploit#
No public exploit known
History#
- Version 1Record published in the CVE List.
- Version 2Most recent update recorded in the CVE List.