CVE-2026-44223

Vllm 0.18.0 – 0.20.0

Published

12 May 2026

Modified

22 June 2026

Patch / advisory

View advisory

CVSS Score v3.1 6.5

Click a component to see what it means

Raw vector

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

EPSS Score 0.0037 30th percentile

Risk Priority 50 floored blend · peak EPSS

Summary

CVE-2026-44223 is a medium-severity Incorrect Calculation of Buffer Size (CWE-131) vulnerability in Vllm Vllm. Its CVSS base score is 6.5 (Medium).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploitation for Privilege Escalation (T1068); ranked at the 30th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as NLP and Transformers; in the Not Applicable risk domain.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SA-15 (Development Process, Standards, and Tools) — see the control section below for these in your framework.

EU & UK References

🇪🇺 ENISA EUVD: EUVD-2026-29800

Vulnerability Data

vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that…

crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.

CWE(s): CWE-131 CWE-704

AI Security AnalysisAI

AI Category: NLP and Transformers
Risk Domain: Not Applicable
OWASP Top 10 for LLMs 2025: None mapped
Classification Reason: Matched keywords: llms, vllm

Related Threats

MITRE ATT&CK Enterprise Techniques

T1068 Exploitation for Privilege Escalation Privilege Escalation

Adversaries may exploit software vulnerabilities in an attempt to elevate privileges.

attack.mitre.org →

T1190 Exploit Public-Facing Application Initial Access

Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.

attack.mitre.org →

T1203 Exploitation for Client Execution Execution

Adversaries may exploit software vulnerabilities in client applications to execute code.

attack.mitre.org →

T1210 Exploitation of Remote Services Lateral Movement

Adversaries may exploit remote services to gain unauthorized access to internal systems once inside of a network.

attack.mitre.org →

T1212 Exploitation for Credential Access Credential Access

Adversaries may exploit software vulnerabilities in an attempt to collect credentials.

attack.mitre.org →

T1687 Exploitation for Defense Impairment Defense Impairment

Adversaries may exploit vulnerabilities in security software, infrastructure, or defensive components to degrade, disable, or otherwise continue to impair their ability to prevent, detect, or respond to malicious activity.

attack.mitre.org →

Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2025-62164Same product: Vllm Vllm

CVE-2025-62372Same product: Vllm Vllm

CVE-2026-44222Same product: Vllm Vllm

CVE-2025-48944Same product: Vllm Vllm

CVE-2026-34760Same product: Vllm Vllm

CVE-2024-11041Same product: Vllm Vllm

CVE-2025-24357Same product: Vllm Vllm

CVE-2025-47277Same product: Vllm Vllm

CVE-2025-30165Same product: Vllm Vllm

CVE-2025-32444Same product: Vllm Vllm

Affected Assets

vllm

0.18.0 — 0.20.0

Mitigating Controls

Mitigating Controls (NIST 800-53 r5) AI

SA-11 Developer Testing and Evaluation good match

Developer security testing and code review can discover incorrect buffer-size computations before deployment.

SA-15 Development Process, Standards, and Tools partial match

Requiring documented development standards and tools can mandate safe typing, casting rules, and compiler checks that stop the weakness from being introduced.

SA-8 Security and Privacy Engineering Principles partial match

Secure engineering principles directly require correct buffer-size arithmetic and bounds-checked allocation.

SI-10 Information Input Validation partial match

Input validation can enforce that supplied lengths or counts used in size calculations are within safe bounds.

SI-16 Memory Protection partial match

Memory-protection mechanisms limit the exploitability of an overflow that results from an incorrect size calculation.

SI-2 Flaw Remediation partial match

Flaw-remediation processes that include vulnerability scanning or static analysis will surface buffer-size errors.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-06 mostly match

prevents

Secure SDLC practices directly prevent buffer-size miscalculations via coding standards, reviews, and testing, while fixing this single weakness only partially fulfills the broader control.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

A.8.28 Secure coding mostly match

degrades

Secure coding standards directly require correct buffer-size calculations.

A.8.29 Security testing in development and acceptance mostly match

finds

Security testing can detect buffer-size errors before release.

A.8.25 Secure development life cycle partial match

prevents

Secure development lifecycle mandates size-checking practices that reduce buffer-size miscalculations.

A.8.26 Application security requirements partial match

prevents

Application security requirements can specify buffer-size validation rules.