CVE-2026-90554

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.

Vllm

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…

12. Sep 2026

Ausgewertete Quellen

• Hinweis
  https://www.vulncheck.com/advisories/vllm-before-0.28.0-denial-of-service-via-audio-extraction
• NVD
  CVE-2026-90554
• GitHub
  https://github.com/vllm-project/vllm/security/advisories/GHSA-936p-m5pv-vvjf