CVE-2026-44222
CWE-129Published: May 12, 2026· Updated: May 14, 2026
Official 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.
Technical Analysis
CVE-2026-44222 can be exploited remotely over the network without requiring physical or adjacent access, significantly expanding the attack surface for threat actors.
The vulnerability requires no privileges and no user interaction, making it a prime target for automated exploitation campaigns and worm-like propagation.
A successful exploit results in availability disruption (denial of service), with a CVSS base score of 7.5.
CVSS v3.1 Vector Breakdown
Affected Vendors & Products
Exploit & PoC Resources
Official Patches & Advisories
All References (2)
Quick Facts
Related CVEs (CWE-129)
Recommended Actions
- →Apply vendor patches immediately
- →Monitor CVE-2026-44222 in threat intel feeds
- →Review IDS/IPS signatures for exploitation attempts