VDB
CISA-2026-22773
CISA-2026-22773
PUBLISHED
CVSS 6.5 MEDIUM
Reported by GitHub_M · Published January 10, 2026
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.
Risk Scores
CVSS 3.1
6.5
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.6.4, < 0.12.0 |
| vllm-project | vllm | >= 0.6.4, < 0.12.0, >= 0.6.4, < 0.12.0 |
Timeline
- Jan 10, 2026 CVE Published
- Jan 12, 2026 CVE Updated
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-grg2-63fw-f2qr x_refsource_CONFIRM