How severe is CVE-2026-44223?

CVE-2026-44223 has a CVSS 3.x base score of 6.5, rated medium severity. It is exploitable over network with low attack complexity, requires low privileges and no user interaction. Impact on confidentiality is none, integrity none, and availability high.

Is CVE-2026-44223 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (29th percentile), an estimate of the probability of exploitation in the next 30 days.

What products are affected by CVE-2026-44223?

CVE-2026-44223 affects Vllm. See the affected-products list for the exact vulnerable versions.

How do I fix CVE-2026-44223?

Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.

Does CVE-2026-44223 have an EU (EUVD) identifier?

Yes. CVE-2026-44223 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-29800.

When was CVE-2026-44223 published?

CVE-2026-44223 was published on 2026-05-12 and last updated on 2026-06-22.

CVE-2026-44223

CVE-2026-44223 is a medium-severity vulnerability in Vllm with a CVSS 3.x base score of 6.5. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-131.

Key facts

Severity: Medium (CVSS 3.x base score 6.5)
EPSS exploit prediction: 0% (29th percentile)
Actively exploited: Not listed in CISA KEV
EU (EUVD) id: EUVD-2026-29800
Weakness: CWE-131
Affected product: Vllm
Published: 2026-05-12
Last modified: 2026-06-22

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.

Frequently asked questions

What is CVE-2026-44223?: 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.
How severe is CVE-2026-44223?: CVE-2026-44223 has a CVSS 3.x base score of 6.5, rated medium severity. It is exploitable over network with low attack complexity, requires low privileges and no user interaction. Impact on confidentiality is none, integrity none, and availability high.
Is CVE-2026-44223 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (29th percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2026-44223?: CVE-2026-44223 affects Vllm. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2026-44223?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.
Does CVE-2026-44223 have an EU (EUVD) identifier?: Yes. CVE-2026-44223 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-29800.
When was CVE-2026-44223 published?: CVE-2026-44223 was published on 2026-05-12 and last updated on 2026-06-22.

References

Affected products (1)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

More vulnerabilities in Vllm

CVE-2025-32444 — Critical (CVSS 10.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and…
CVE-2026-22778 — Critical (CVSS 9.8): vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid…
CVE-2025-47277 — Critical (CVSS 9.8): vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4…
CVE-2024-11041 — Critical (CVSS 9.8): vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses…
CVE-2026-48746 — Critical (CVSS 9.1): vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in…
CVE-2025-29783 — Critical (CVSS 9.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use…

All CVEs affecting Vllm →

Other CWE-131 (Incorrect Calculation of Buffer Size) vulnerabilities

CVE-2026-52955 — Critical (CVSS 9.8): In the Linux kernel, the following vulnerability has been resolved: libceph: Fix potential out-of-bounds access in…
CVE-2026-41676 — Critical (CVSS 9.8): rust-openssl provides OpenSSL bindings for the Rust programming language. From 0.9.27 to before 0.10.78,…
CVE-2026-1949 — Critical (CVSS 9.8): Delta Electronics AS320T has incorrect calculation of the buffer size on the stack in the GET/PUT request handler of…
CVE-2026-20911 — Critical (CVSS 9.8): A heap-based buffer overflow vulnerability exists in the HuffTable::initval functionality of LibRaw Commit 0b56545 and…
CVE-2025-1861 — Critical (CVSS 9.8): In PHP from 8.1.* before 8.1.32, from 8.2.* before 8.2.28, from 8.3.* before 8.3.19, from 8.4.* before 8.4.5, when…
CVE-2023-5941 — Critical (CVSS 9.8): In versions of FreeBSD 12.4-RELEASE prior to 12.4-RELEASE-p7 and FreeBSD 13.2-RELEASE prior to 13.2-RELEASE-p5 the…

Browse all CWE-131 (Incorrect Calculation of Buffer Size) vulnerabilities →