CVE-2026-44222

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 v3.1 Score

6.5

MEDIUM

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

EPSS — Exploit Prediction

0.0001

Probability of exploitation

0.03%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-129 CWE-129

Affected Products

Vendor	Product	Versions
vllm	vllm	0.6.1 — 0.20.0

References

Advisories & Patches

https://github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59f

Exploits

https://github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59f

Other References

https://github.com/vllm-project/vllm/issues/32656

Frequently Asked Questions

What is CVE-2026-44222? +

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. It has a CVSS v3.1 base score of 6.5 (MEDIUM).

How severe is CVE-2026-44222? +

CVE-2026-44222 has a CVSS v3.1 score of 6.5 out of 10, rated MEDIUM. This is a medium-severity vulnerability that should be remediated as part of regular maintenance. The EPSS score is 0.0001, placing it in the 0th percentile for exploitation probability.

What products are affected by CVE-2026-44222? +

CVE-2026-44222 affects products from vllm, specifically: vllm. Check the affected products table above for specific version ranges.

How do I check if I'm vulnerable to CVE-2026-44222? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2025-0657

A weakness in Automated Logic and Carrier i-Vu Gen5 router on driver version drv_gen5_106-01-2380, allows malformed packets to be sent …

CVE-2025-66559

Taiko Alethia is an Ethereum-equivalent, permissionless, based rollup designed to scale Ethereum without compromising its fundamental properties. In 2.3.1 and …

CVE-2023-31309

Improper validation in Power Management Firmware (PMFW) may allow an attacker with privileges to pass malformed workload arguments when exporting …

CVE-2024-45569 9.8

Memory corruption while parsing the ML IE due to invalid frame content.

CVE-2024-24563 9.8

Vyper is a Pythonic Smart Contract Language for the Ethereum Virtual Machine. Arrays can be keyed by a signed integer, …

CVE-2024-31581 9.8

FFmpeg version n6.1 was discovered to contain an improper validation of array index vulnerability in libavcodec/cbs_h266_syntax_template.c. This vulnerability allows attackers …