vllm-project · vLLM · published 2026-01-10

CVE-2026-22773vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions

Routine No exploitation evidence; EPSS 0.4%.

CVE-2026-22773 is not known to be exploited in the wild. EPSS estimates a 0.4% chance of exploitation in the next 30 days, higher than 39% of all CVEs. This vLLM vulnerability: CVSS 6.5 (v3.1). Fixed upstream in vLLM 0.12.0. Routine: patch when convenient.

Share this

Remediation#

Fixed upstream in vLLM 0.12.0.

Patch events

  1. This monthSecurity release

    AI toolingvLLM

    vLLM security release: 0.12.0

    Upgrade to 0.12.0

    Why: Vendor security release for server software (most severe: CVE-2026-22773).

Exploit intelligence#

SignalValueSource
Known exploitedNoCISA KEV
Ransomware use—CISA KEV
EPSS (30-day exploitation probability)0.4% (39th pct)FIRST EPSS v2026.06.15
CVSS base score6.5 (v3.1)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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 is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime error, leading to complete server termination. This issue has been patched in version 0.12.0.

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 →