CVE-2026-55646: fallo de gravedad media en vllm-project vllm
vLLM speech-to-text endpoints allocate full upload before enforcing the audio file-size limit
Publicada el
Aviso por correo cuando entre en el KEV, tenga PoC pública o suba de nota.
13Vexday Risk Score
Sin señal de explotación. Ningún artefacto público de explotación conocido hasta ahora.
ssvc Trackcvss 6.5epss 0.5%
vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read() to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed upload size limit (default 25 MB) later in the speech-to-text preprocessing step, so an API caller who can reach those routes can submit an oversized multipart upload and cause vLLM to allocate memory proportional to the uploaded file size before the request is rejected as too large, creating memory pressure or terminating the process depending on deployment resource limits. This issue is fixed in version 0.24.0.
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Productos afectados
vllm-project · vllmCVEs relacionadas — vllm-project vllm
En el mismo producto, de las más peligrosas a las menos.
CVE-2026-22778CRITICALvLLM leaks a heap address when PIL throws an errorEPSS 18.3%CVE-2025-32444CRITICALvLLM Vulnerable to Remote Code Execution via Mooncake IntegrationEPSS 1.8%CVE-2026-27893HIGHvLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-outEPSS 1.4%CVE-2026-48746CRITICALvLLM: OpenAI auth bypassEPSS 1.2%CVE-2026-22807HIGHvLLM affected by RCE via auto_map dynamic module loading during model initializationEPSS 1.0%CVE-2025-47277CRITICALvLLM Allows Remote Code Execution via PyNcclPipe Communication ServiceEPSS 1.0%