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.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.12.0.
Patch events
AI toolingvLLM
vLLM security release: 0.12.0
Upgrade to
0.12.0Why: Vendor security release for server software (most severe: CVE-2026-22773).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.4% (39th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 6.5 (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 exploitation | none | CISA Vulnrichment |
| SSVC automatable | No | CISA Vulnrichment |
| SSVC technical impact | partial | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
>= 0.6.4, < 0.12.0(affected)
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.