vLLM: Remote DoS via Special-Token Placeholders_CVE-2026-44222

6.5 / 10

MEDIUM

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

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.

Basic Information

ID CVE-2026-44222

Source GitHub_M

Published May 12, 2026 at 19:57

Affected Product

Vendor vllm-project

Product vllm

Version >= 0.6.1, < 0.20.0

Affected Versions vllm-project vllm >= 0.6.1, < 0.20.0

CWE Classification

CWE-129

References

{
    "lastseen": "",
    "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\u2019s 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.",
    "published": "2026-05-12T19:57:25.336Z",
    "modified": "2026-05-12T19:57:25.336Z",
    "type": "cve",
    "title": "vLLM: Remote DoS via Special-Token Placeholders",
    "source": "GitHub_M",
    "references": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59f\nhttps://github.com/vllm-project/vllm/issues/32656",
    "id": "CVE-2026-44222",
    "bulletinFamily": "",
    "cwe": [
        "CWE-129"
    ],
    "cvelist": null,
    "sourceData": "vllm-project vllm >= 0.6.1, < 0.20.0",
    "sourceHref": "",
    "cvss": {
        "score": 6.5,
        "severity": "MEDIUM",
        "vector": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
        "version": "3.1"
    },
    "cvss2": [],
    "cvss3": {
        "version": "",
        "vectorString": "",
        "baseScore": 0,
        "baseSeverity": "",
        "attackVector": "",
        "attackComplexity": "",
        "privilegesRequired": "",
        "userInteraction": "",
        "scope": "",
        "confidentialityImpact": "",
        "integrityImpact": "",
        "availabilityImpact": "",
        "cvssV3": {
            "version": "",
            "vectorString": "",
            "baseScore": 0,
            "baseSeverity": "",
            "attackVector": "",
            "attackComplexity": "",
            "privilegesRequired": "",
            "userInteraction": "",
            "scope": "",
            "confidentialityImpact": "",
            "integrityImpact": "",
            "availabilityImpact": ""
        }
    },
    "href": "",
    "category_name": "CVE",
    "post_link": "",
    "product": "vllm",
    "version": ">= 0.6.1, < 0.20.0",
    "vendor": "vllm-project",
    "ai_description": "",
    "ai_severity": "",
    "ai_vendor": "",
    "ai_product": "",
    "ai_version": "",
    "ai_score": 0
}