Resource exhaustion in Vllm
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. 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.
Vulnerability class: DoS (Denial of Service)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 6.2 (Medium). Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.
EPSS exploit prediction
EPSS: 0.002 (9.8th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 10th percentile — 9.8% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.002 · newest: 0.002 · change: 0.000
Affected products
Weakness classification (CWE)
References
- github.com/vllm-project/vllm/security/advisories/GHSA-936p-m5pv-vvjf (vendor-advisory, Vendor Advisory)
- www.vulncheck.com/advisories/vllm-before-0.28.0-denial-of-service-via-audio-ext… (Third Party Advisory, third-party-advisory)
Frequently asked questions
- What is CVE-2026-90554?
- CVE-2026-90554 is a medium-severity vulnerability in Vllm, classified under Uncontrolled Resource Consumption. CVSS score: 6.2/10. Published 2026-09-12.
- How severe is CVE-2026-90554?
- Medium severity. CVSS v3 base score is 6.2 out of 10.