6.5
CVE-2026-57173
- EPSS 0.66%
- Veröffentlicht 16.09.2026 16:34:39
- Zuletzt bearbeitet 07.10.2026 14:24:22
- Erkennungen
vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions
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.
| Typ | Quelle | Score | Percentile |
|---|---|---|---|
| EPSS | FIRST.org | 0.66% | 0.5 |
| Quelle | Base Score | Exploit Score | Impact Score | Vector String |
|---|---|---|---|---|
| security-advisories@github.com | 6.5 | 2.8 | 3.6 |
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
|
CWE-770 Allocation of Resources Without Limits or Throttling
The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.
https://github.com/vllm-project/vllm/releases/tag/v0.24.0
https://github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcr
https://github.com/vllm-project/vllm/pull/45908
https://github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965e