Skip to content
Fencer Intel
medium 6.2

CVE-2026-90554 json

vLLM before 0.28.0 Denial of Service via audio extraction

published 2mo ago modified last mo. also EUVD-2026-76872 , GHSA-936p-m5pv-vvjf

Unreviewed: the maintainers' own advisory

Published by the maintainers on their GitHub repository vllm-project/vllm. GitHub has not reviewed it into the GitHub Advisory Database, so the affected packages and versions are the maintainers' word. Read the full advisory on GitHub.

cvss
6.2
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.2%
EPSS 0.2% chance of exploitation in 30 days, percentile 10%
public exploits
0
none known

Summary

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.

Patch / fix

  • vllm-project vLLM 0.28.0

Is CVE-2026-90554 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-90554 updated cvss 6.2

vllm: vLLM: Denial of Service via video audio extraction

  • Red Hat AI Inference Server rhaii/vllm-cpu-rhel9, rhaii/vllm-tpu-rhel9, rhaii/vllm-cuda-rhel9, rhaii/vllm-rocm-rhel9, rhaiis/vllm-cpu-rhel9, rhaiis/vllm-tpu-rhel9, +7 more Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-rocm-rhel9, rhelai3/bootc-gaudi-rhel9, rhelai3/bootc-aws-cuda-rhel9, rhelai3/bootc-gcp-cuda-rhel9, rhelai3/bootc-azure-cuda-rhel9, +1 more Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-gaudi-rhel9, rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-llm-d-kv-cache-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-th-torch-cuda-py312-rhel9, +1 more
    affected: workaround, no fix available “Fix deferred”

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
last mo.

Exploit prediction

0.20% chance of exploitation in the next 30 days, higher than 10% of all scored CVEs (FIRST EPSS, 2026-11-11).

CVSS scores

assigned by version score vector
CNA 4.0 6.9 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
CNA 3.1 6.2 CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CNA 4.0 6.9 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
NVD 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Inferred packages

No advisory lists a package for this vulnerability yet. The CVE names these as products and links their GitHub repository, and the package registry names the same repository, so they are probably the affected packages. Low confidence: the versions are the CVE’s own for the product, and a stack check reports the package as unchecked when there are none.

ecosystem package repository affected
pypi vllm vllm-project/vllm no versions given

Affected products

  • vllm-project vLLM

Classification

Weakness
  • CWE-400 Uncontrolled Resource Consumption

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

The maintainers of vllm-project/vllm published their own advisory on GitHub. Reviewed sources take precedence over it.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.