What’s Vulnerable › Vulnerabilities

CVE-2026-44222: vLLM: Remote DoS via Special-Token Placeholders

• Severity: high (CVSS 7.5 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.4% probability of exploitation in the next 30 days
• Public exploit or detection template: yes
• Published: 2026-05-12 · updated 2026-06-17
• Weakness: CWE-129

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.

Affected products

• vllm-project vllm: from 0.6.1 before 0.20.0 — fixed in 0.20.0

How to fix

Upgrade to a fixed version: vllm-project vllm 0.20.0. Check the vendor advisory for mitigations.

References

• https://github.com/vllm-project/vllm/issues/32656
• https://github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59f

Get alerted when CVE-2026-44222 or the next vulnerability affects your stack