CVE-2026-90554

Description

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.

References

https://www.vulncheck.com/advisories/vllm-before-0.28.0-denial-of-service-via-audio-extraction

https://github.com/vllm-project/vllm/security/advisories/GHSA-936p-m5pv-vvjf

Details

Source: Mitre, NVD

Risk Information

CVSS v2

CVSS v3

CVSS v4