CVE-2026-44222
vLLM is an inference and serving engine for large language models …
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.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59f
- github.com/vllm-project/vllm/issues/32656
- github.com/advisories/GHSA-hpv8-x276-m59f
- nvd.nist.gov/vuln/detail/CVE-2026-44222
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-3409.yaml
- github.com/vllm-project/vllm
- pypi.org/project/vllm
- nvd.nist.gov/vuln/detail/CVE-2026-44222
- cve.org/CVERecord?id=CVE-2026-44222
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.