CVE-2026-57173
vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Fuente: CNA
Ciclo de vida de la vulnerabilidad
| Fecha | Fase | Evento | Detalle |
|---|---|---|---|
| Remediación | Parche 0.24.0 | vllm · -78 d desde divulgación | |
| Divulgación | Publicada | CVE-2026-57173 divulgada · CVSS 6.5 (CNA) | |
| Divulgación | Evaluación SSVC | CISA-ADP · explotación ninguna | |
| Divulgación | Modificada | Última actualización del registro | |
| Monitoreo | Detectada | Ingresó al índice |
vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the input_audio handling path for /v1/chat/completions calls AudioMediaIO.load_bytes or AudioMediaIO.load_file without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio decoder. An unauthenticated client can therefore submit a small compressed audio input that expands into a very large float32 PCM allocation, bypassing the duration guard already used by /v1/audio/transcriptions and causing an out-of-memory worker crash. Inline data URLs reach this path without being bounded by VLLM_AUDIO_FETCH_TIMEOUT. The issue affects deployments serving an audio-capable model, and authentication changes only the deployment-specific reachability. This issue is fixed in version 0.24.0.
Desglose de métricas
Rangos afectados
Estado del parche por paquete
| Paquete / producto | Estado | Corregida en | Desde divulgación | Última versión |
|---|---|---|---|---|
pypivllm |
Corregida | 0.24.0 | -78 d | 0.33.0 no afectada |
0.24.0Arsenal público
Sin exploits, módulos ni PoC públicos conocidos a la fecha de verificación.
https://github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcrhttps://github.com/vllm-project/vllm/pull/45908https://github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965ehttps://github.com/vllm-project/vllm/releases/tag/v0.24.0Las referencias externas se muestran para copiar: cve.llama.ec no lo redirige a otros sitios.
