vllm-project · vLLM · published 2026-09-12

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

Routine No exploitation evidence; EPSS 0.2%.

CVE-2026-90554 is not known to be exploited in the wild. EPSS estimates a 0.2% chance of exploitation in the next 30 days, higher than 10% of all CVEs. This vLLM vulnerability: CVSS 6.9 (v4.0). Fixed upstream in vLLM 0.28.0. Routine: patch when convenient.

Share this

Remediation#

Fixed upstream in vLLM 0.28.0.

Patch events

  1. This monthSecurity release

    AI toolingvLLM

    vLLM security release: 0.28.0

    Upgrade to 0.28.0

    Why: CVE-2026-69147: Public proof-of-concept exists (SSVC exploitation: poc).

Exploit intelligence#

SignalValueSource
Known exploitedNoCISA KEV
Ransomware use—CISA KEV
EPSS (30-day exploitation probability)0.2% (10th pct)FIRST EPSS v2026.06.15
CVSS base score6.9 (v4.0)
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 / CISA ADP
SSVC exploitationnoneCISA Vulnrichment
SSVC automatableNoCISA Vulnrichment
SSVC technical impactpartialCISA Vulnrichment

Affected versions (from the CVE record)#

Description (from the CVE record)#

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.

Quoted from the CVE Program record.

Elsewhere#

Distro status: Debian · Ubuntu · Red Hat · Alpine

Something wrong on this page?
Anonymous. Reports are checked against the primary source.

Also on today's list

See today's list → · Coming up →