How severe is CVE-2025-62372?

CVE-2025-62372 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-2025-62372 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (25th percentile), an estimate of the probability of exploitation in the next 30 days.

What products are affected by CVE-2025-62372?

CVE-2025-62372 primarily affects Vllm. In total, 3 product configurations (CPEs) are listed as vulnerable; see the affected-products list for the exact versions.

How do I fix CVE-2025-62372?

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

Does CVE-2025-62372 have an EU (EUVD) identifier?

Yes. CVE-2025-62372 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-198357.

When was CVE-2025-62372 published?

CVE-2025-62372 was published on 2025-11-21 and last updated on 2026-06-17.

CVE-2025-62372

CVE-2025-62372 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-129.

Key facts

Severity: Medium (CVSS 3.x base score 6.5)
CVSS v4: 8.3
EPSS exploit prediction: 0% (25th percentile)
Actively exploited: Not listed in CISA KEV
EU (EUVD) id: EUVD-2025-198357
Weakness: CWE-129
Affected product: Vllm
Published: 2025-11-21
Last modified: 2026-06-17

Description

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1.

Frequently asked questions

What is CVE-2025-62372?: vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1.
How severe is CVE-2025-62372?: CVE-2025-62372 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-2025-62372 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (25th percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2025-62372?: CVE-2025-62372 primarily affects Vllm. In total, 3 product configurations (CPEs) are listed as vulnerable; see the affected-products list for the exact versions.
How do I fix CVE-2025-62372?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.
Does CVE-2025-62372 have an EU (EUVD) identifier?: Yes. CVE-2025-62372 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-198357.
When was CVE-2025-62372 published?: CVE-2025-62372 was published on 2025-11-21 and last updated on 2026-06-17.

References

Affected products (3)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
cpe:2.3:a:vllm:vllm:0.11.1:rc0:*:*:*:*:*:*
cpe:2.3:a:vllm:vllm:0.11.1:rc1:*:*:*:*:*:*

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-129 (Improper Validation of Array Index) vulnerabilities

CVE-2020-27485 — Critical (CVSS 9.9): Garmin Forerunner 235 before 8.20 is affected by: Array index error. The component is: ConnectIQ TVM. The attack vector…
CVE-2020-27483 — Critical (CVSS 9.9): Garmin Forerunner 235 before 8.20 is affected by: Array index error. The component is: ConnectIQ TVM. The attack vector…
CVE-2026-21413 — Critical (CVSS 9.8): A heap-based buffer overflow vulnerability exists in the lossless_jpeg_load_raw functionality of LibRaw Commit 0b56545…
CVE-2025-27034 — Critical (CVSS 9.8): Memory corruption while selecting the PLMN from SOR failed list.
CVE-2025-3357 — Critical (CVSS 9.8): IBM Tivoli Monitoring 6.3.0.7 through 6.3.0.7 Service Pack 19 could allow a remote attacker to execute arbitrary code…
CVE-2024-45569 — Critical (CVSS 9.8): Memory corruption while parsing the ML IE due to invalid frame content.

Browse all CWE-129 (Improper Validation of Array Index) vulnerabilities →