Descrição
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.
CVSS 6.5EPSS 0.422%Risco 0.67
Ver fonte- Publicação
- 2026-06-22 23:16:31
- Versões afetadas
- <0.23.1rc0
- Tipo
- Software crítico
- Vetor
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H