| ID |
CVE-2026-57173
|
| Sažetak |
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. |
| Reference |
|
| CVSS |
| Base: | 6.5 |
| Impact: | 3.6 |
| Exploitability: | 2.8 |
|
| Pristup |
| Vektor | Složenost | Autentikacija |
| NETWORK |
LOW |
LOW |
|
| Impact |
| Povjerljivost | Cjelovitost | Dostupnost |
| NONE |
NONE |
HIGH |
|
| CVSS vektor |
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |
| Zadnje važnije ažuriranje |
18-09-2026 - 18:17 |
| Objavljeno |
16-09-2026 - 17:17 |
