Vulnerability Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0.
CVSS Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.6.1, < 0.20.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/issues/32656Issue Tracking
- https://github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59fExploitVendor Advisory
FAQ
What is CVE-2026-44222?
CVE-2026-44222 is a vulnerability with a CVSS score of 6.5 (MEDIUM). vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text...
How severe is CVE-2026-44222?
CVE-2026-44222 has been rated MEDIUM with a CVSS base score of 6.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-44222?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.