Skip to main content
Press slash or control plus K to focus the search. Use the arrow keys to navigate results and press enter to open a threat.
Reconnecting to live updates…
EPSS 0.4%top 71%

CVE-2026-44223: CWE-131: Incorrect Calculation of Buffer Size in vllm-project vllm

0
Medium
VulnerabilityCVE-2026-44223cvecve-2026-44223cwe-131cwe-704
Published: 05/12/2026 (05/12/2026, 19:58:40 UTC)
Source: CVE Database V5
Vendor/Project: vllm-project
Product: vllm

Description

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.

CVSS v3.1

Score 6.5medium

Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Affected software

GitHub Actionsmore threats →ai
vllm-project/vllm
pkg:github/vllm-project/vllm
Affected versions
<0.20.0

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 06/23/2026, 14:17:06 UTC

Technical Analysis

CVE-2026-44223 describes a vulnerability in vLLM (versions 0.18.0 up to but not including 0.20.0) where the extract_hidden_states speculative decoding proposer returns a tensor with an incorrect shape after the first decode step if any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). This causes a RuntimeError that crashes the EngineCore process, resulting in denial of service. The vulnerability is due to incorrect calculation of buffer size (CWE-131) and improper handling of speculative decoding (CWE-704). The issue is resolved in vLLM version 0.20.0.

Potential Impact

The vulnerability causes a denial of service by crashing the EngineCore process of vLLM when a request includes sampling penalty parameters. This can disrupt availability of the inference and serving engine for large language models. There is no impact on confidentiality or integrity reported. No known exploits in the wild have been documented.

Mitigation Recommendations

Upgrade vLLM to version 0.20.0 or later, where this vulnerability is fixed. No other mitigation or workaround is indicated. Patch status is confirmed by the vendor stating the issue is fixed in 0.20.0.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
GitHub_M
Date Reserved
2026-05-05T15:42:40.518Z
Cvss Version
3.1
State
PUBLISHED
Remediation Level
null

Threat ID: 6a038bd7cbff5d8610164968

Added to database: 05/12/2026, 20:21:43 UTC

Last enriched: 06/23/2026, 14:17:06 UTC

Last updated: 07/03/2026, 04:39:16 UTC

Views: 127

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses