CVE-2026-44222

vLLM: Remote DoS via Special-Token Placeholders

MEDIUM 6.5

At a glance

Source
NVD
EPSS
EPSS 0.41 % · percentile 36 ()
State
PUBLISHED
Published
Updated
Assigner
GitHub_M
NVD status
Analyzed

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.

Weaknesses (CWE)

  • CWE-129 — Improper Validation of Array Index

References

Scores

VersionScoreVectorScored by
CVSS 3.1MEDIUM 6.5CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:HGitHub_M
CVSS 3.1MEDIUM 6.5CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:HNVD · security-advisories@github.com (Secondary)
CVSS 3.1HIGH 7.5CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:HNVD · nvd@nist.gov (Primary)

Advisories

European references

Affected configurations (NVD CPE)

Affected products

ProductVersions
vllm-project · vllmaffected >= 0.6.1, < 0.20.0

Sources

SourceLicence
CVE List (CVEProject cvelistV5)CVE Program Terms of Use
EPSS (FIRST.org)FIRST — attribution requested
ENISA EUVDENISA — reproduction authorised, source acknowledged
NVD (NIST) via fkie-cad/nvd-json-data-feedsPublic domain — this product uses data from the NVD API but is not endorsed or certified by the NVD