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.

Attack Vector Local

Attack Complexity Low

Privileges Required None

Attack Requirements None

User Interaction None

Vulnerable System Confidentiality Impact None

Vulnerable System Integrity Impact None

Vulnerable System Availability Impact High

Subsequent System Confidentiality Impact None

Subsequent System Integrity Impact None

Subsequent System Availability Impact None

Attack Vector Local

Attack Complexity Low

Privileges Required None

Scope Unchanged

Confidentiality Impact None

Integrity Impact None

Availability Impact High

User Interaction None

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

No EPSS score available.

Key SSVC decision points have not yet been added.

Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).

Vendor Product Default status Versions
vllm-project vLLM unaffected
Version Status Constraints
0.10.2 affected < 0.28.0
0.28.0 unaffected —

No data.

No data.

No data.

Project Subscriptions

Vendors Products
Vllm Subscribe
Vllm Subscribe
Advisories

No advisories yet.

Fixes

Solution

No solution given by the vendor.

Workaround

No workaround given by the vendor.

References
Link Providers
https://github.com/vllm-project/vllm/security/advisories/GHSA-936p-m5pv-vvjf cve-icon cve-icon
https://www.vulncheck.com/advisories/vllm-before-0.28.0-denial-of-service-via-audio-extraction cve-icon cve-icon
History

Sat, 12 Sep 2026 12:30:00 +0000

Type Values Removed Values Added
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.
Title vLLM before 0.28.0 Denial of Service via audio extraction
First Time appeared Vllm
Vllm vllm
Weaknesses CWE-400
CPEs cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
Vendors & Products Vllm
Vllm vllm
References
Metrics cvssV3_1

{'score': 6.2, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H'}

cvssV4_0

{'score': 6.9, 'vector': 'CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N'}

Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: VulnCheck

Published:

Updated: 2026-09-12T12:08:57.508Z

Reserved: 2026-09-12T11:13:43.326Z

Link: CVE-2026-90554

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-09-12T13:16:54.040

Modified: 2026-09-12T13:16:54.040

Link: CVE-2026-90554

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.

Weaknesses