CVE-2026-90554

published 12 Sep 2026 · updated 14 Sep 2026

vLLM before 0.28.0 Denial of Service via audio extraction

6.2MediumCVSS 6.2EPSS 0%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. Fixed in 0.28.0.

vLLM versions >=0.10.2 and <0.28.0 do not apply any audio decode-size or duration limit when extracting audio from video input for NanoNemotronVL models. In nano_nemotron_vl.py, _extract_audio_from_videos calls load_audio_pyav(BytesIO(video_bytes)) without the max_duration_s or max_decode_bytes parameters, so neither VLLM_MAX_AUDIO_DECODE_DURATION_S nor VLLM_MAX_AUDIO_DECODE_BYTES is enforced (unlike the direct audio upload path in AudioMediaIO). When a NanoNemotronVL model is served with use_audio_in_video=True, an attacker who supplies a small, highly compressed video as multimodal input can force the server to allocate gigabytes of memory during audio decoding, resulting in a denial of service. Fixed in vLLM 0.28.0.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
vllm-project>=0.10.2 <0.28.00.28.0

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-90554 severity on Zeptric[![CVE-2026-90554](https://zeptric.io/badge/cve/CVE-2026-90554.svg)](https://zeptric.io/cve/CVE-2026-90554)