What’s Vulnerable › Vulnerabilities

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

• Severity: high (CVSS 7.5 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.2% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-09-12 · updated 2026-09-24
• Weakness: CWE-400

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.

Affected products

• vllm-project vllm: from 0.10.2 before 0.28.0 — fixed in 0.28.0

How to fix

Upgrade to a fixed version: vllm-project vllm 0.28.0. Check the vendor advisory for mitigations.

References

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

Get alerted when CVE-2026-90554 or the next vulnerability affects your stack