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.

CVSS

No CVSS.

References

Link	Resource
https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b
https://github.com/vllm-project/vllm/pull/27204
https://github.com/vllm-project/vllm/pull/6613
https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw

Configurations

No configuration.

History

21 Nov 2025, 02:15

Type	Values Removed	Values Added
New CVE

Information

Published : 2025-11-21 02:15

Updated : 2025-11-21 15:13

NVD link : CVE-2025-62372

Mitre link : CVE-2025-62372

CVE.ORG link : CVE-2025-62372

JSON object : View

Products Affected

No product.

CWE

CWE-129

Improper Validation of Array Index

{"id": "CVE-2025-62372", "cveTags": [], "metrics": {"cvssMetricV40": [{"type": "Secondary", "source": "[email protected]", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 8.3, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "HIGH", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "NONE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "LOW", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "NONE", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "HIGH", "vulnAvailabilityImpact": "HIGH", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "NONE", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "published": "2025-11-21T02:15:43.393", "references": [{"url": "https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b", "source": "[email protected]"}, {"url": "https://github.com/vllm-project/vllm/pull/27204", "source": "[email protected]"}, {"url": "https://github.com/vllm-project/vllm/pull/6613", "source": "[email protected]"}, {"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw", "source": "[email protected]"}], "vulnStatus": "Awaiting Analysis", "weaknesses": [{"type": "Primary", "source": "[email protected]", "description": [{"lang": "en", "value": "CWE-129"}]}], "descriptions": [{"lang": "en", "value": "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."}], "lastModified": "2025-11-21T15:13:13.800", "sourceIdentifier": "[email protected]"}