CVE-2026-90554: vLLM before 0.28.0 Denial of Service via audio extraction

Published Sep 12, 2026
·
Updated

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 nanonemotronvl.py, extractaudiofromvideos calls loadaudiopyav(BytesIO(videobytes)) without the maxdurations or maxdecodebytes parameters, so neither VLLMMAXAUDIODECODEDURATIONS nor VLLMMAXAUDIODECODEBYTES is enforced (unlike the direct audio upload path in AudioMediaIO). When a NanoNemotronVL model is served with useaudioinvideo=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 Software

1 affected component
vllm vllm>=0.10.2, <0.28.0

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade vLLM to a version that resolves this vulnerability.

    Fixed in 0.28.0
  2. Configuration

    For NanoNemotronVL with use_audio_in_video=True, ensure _extract_audio_from_videos passes the max_duration_s and max_decode_bytes parameters to load_audio_pyav(BytesIO(video_bytes)) so VLLM_MAX_AUDIO_DECODE_DURATION_S and VLLM_MAX_AUDIO_DECODE_BYTES are enforced during audio decoding.

    vLLM (nano_nemotron_vl.py / _extract_audio_from_videos) Enforce audio decode limits for load_audio_pyav(BytesIO(video_bytes) = Apply VLLM_MAX_AUDIO_DECODE_DURATION_S and VLLM_MAX_AUDIO_DECODE_BYTES when calling load_audio_pyav for video-derived audio extraction

Event History

Sep 12, 2026
CVE Published
via MITRE·12:08 PM
Data Sourced
via MITRE·12:08 PM
DescriptionSeverityWeakness

Frequently Asked Questions

1

Which deployments are exposed to this issue?

Deployments running vLLM versions 0.10.2 through before 0.28.0 are exposed only when serving a NanoNemotronVL model with use_audio_in_video=True. The affected path is video input processing that extracts audio.

2

What does an attacker need to do to trigger the denial of service?

An attacker needs to submit a multimodal video input containing highly compressed audio that expands substantially during decoding. No privileges or user interaction are required according to the supplied severity vector.

3

Do the audio decoding environment limits mitigate this issue?

No. VLLM_MAX_AUDIO_DECODE_DURATION_S and VLLM_MAX_AUDIO_DECODE_BYTES are not enforced on the vulnerable audio-from-video extraction path, even though they are used for direct audio uploads.

4

What should teams do if they cannot immediately upgrade?

Avoid serving NanoNemotronVL with use_audio_in_video=True or prevent untrusted users from submitting video multimodal inputs. Upgrading to vLLM 0.28.0 fixes the issue.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203