CVE-2026-22773
HIGH EPSS 32.2%
Published Jan 10, 20265mo ago · Modified Jun 17, 20261w ago
7.5 CVSS 3.1
Published Jan 10, 2026 5mo ago
Last Modified Jun 17, 2026 1w ago
Description
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.
CVSS Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction None
Scope Unchanged
Confidentiality None
Integrity None
Availability High
Threat Intelligence
EPSS Exploit Probability
32.2% percentile
Exploit & Patch Status
Public Exploit Known
No Patch Available
Weaknesses 1
CWE-770
Affected Products 1
| Vendor | Product | Version | Range |
|---|---|---|---|
| vllm | vllm | * | ≥0.6.4 – <0.12.0 |
References 1
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-grg2-63fw-f2qr
Remediation
No remediation data recorded yet
Check vendor advisories and the NVD entry for patch availability.