{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2025-62372", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2025-10-10T14:22:48.204Z", "datePublished": "2025-11-21T01:22:37.121Z", "dateUpdated": "2025-11-24T18:11:59.207Z"}, "containers": {"cna": {"title": "vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs", "problemTypes": [{"descriptions": [{"cweId": "CWE-129", "lang": "en", "description": "CWE-129: Improper Validation of Array Index", "type": "CWE"}]}], "metrics": [{"cvssV4_0": {"attackVector": "NETWORK", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "LOW", "userInteraction": "NONE", "vulnConfidentialityImpact": "NONE", "vulnIntegrityImpact": "NONE", "vulnAvailabilityImpact": "HIGH", "subConfidentialityImpact": "NONE", "subIntegrityImpact": "NONE", "subAvailabilityImpact": "HIGH", "baseScore": 8.3, "baseSeverity": "HIGH", "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", "version": "4.0"}}], "references": [{"name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw"}, {"name": "https://github.com/vllm-project/vllm/pull/27204", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/27204"}, {"name": "https://github.com/vllm-project/vllm/pull/6613", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/6613"}, {"name": "https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b"}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"version": ">= 0.5.5, < 0.11.1", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2025-11-21T01:22:37.121Z"}, "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."}], "source": {"advisory": "GHSA-pmqf-x6x8-p7qw", "discovery": "UNKNOWN"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2025-11-24T17:07:55.989854Z", "id": "CVE-2025-62372", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "role": "CISA Coordinator", "version": "2.0.3"}}}], "title": "CISA ADP Vulnrichment", "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2025-11-24T18:11:59.207Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2025-62372", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2025-11-24T17:07:55.989854Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2025-11-24T17:09:03.695Z"}}], "cna": {"title": "vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs", "source": {"advisory": "GHSA-pmqf-x6x8-p7qw", "discovery": "UNKNOWN"}, "metrics": [{"cvssV4_0": {"version": "4.0", "baseScore": 8.3, "attackVector": "NETWORK", "baseSeverity": "HIGH", "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", "userInteraction": "NONE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "LOW", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "NONE", "subAvailabilityImpact": "HIGH", "vulnAvailabilityImpact": "HIGH", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "NONE"}}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"status": "affected", "version": ">= 0.5.5, < 0.11.1"}]}], "references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw", "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw", "tags": ["x_refsource_CONFIRM"]}, {"url": "https://github.com/vllm-project/vllm/pull/27204", "name": "https://github.com/vllm-project/vllm/pull/27204", "tags": ["x_refsource_MISC"]}, {"url": "https://github.com/vllm-project/vllm/pull/6613", "name": "https://github.com/vllm-project/vllm/pull/6613", "tags": ["x_refsource_MISC"]}, {"url": "https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b", "name": "https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b", "tags": ["x_refsource_MISC"]}], "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."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-129", "description": "CWE-129: Improper Validation of Array Index"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2025-11-21T01:22:37.121Z"}}}, "cveMetadata": {"cveId": "CVE-2025-62372", "state": "PUBLISHED", "dateUpdated": "2025-11-24T18:11:59.207Z", "dateReserved": "2025-10-10T14:22:48.204Z", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "datePublished": "2025-11-21T01:22:37.121Z", "assignerShortName": "GitHub_M"}, "dataVersion": "5.2"}

{"cveTags": [], "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."}], "id": "CVE-2025-62372", "lastModified": "2025-11-21T15:13:13.800", "metrics": {"cvssMetricV40": [{"cvssData": {"Automatable": "NOT_DEFINED", "Recovery": "NOT_DEFINED", "Safety": "NOT_DEFINED", "attackComplexity": "LOW", "attackRequirements": "NONE", "attackVector": "NETWORK", "availabilityRequirement": "NOT_DEFINED", "baseScore": 8.3, "baseSeverity": "HIGH", "confidentialityRequirement": "NOT_DEFINED", "exploitMaturity": "NOT_DEFINED", "integrityRequirement": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "privilegesRequired": "LOW", "providerUrgency": "NOT_DEFINED", "subAvailabilityImpact": "HIGH", "subConfidentialityImpact": "NONE", "subIntegrityImpact": "NONE", "userInteraction": "NONE", "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", "version": "4.0", "vulnAvailabilityImpact": "HIGH", "vulnConfidentialityImpact": "NONE", "vulnIntegrityImpact": "NONE", "vulnerabilityResponseEffort": "NOT_DEFINED"}, "source": "[email protected]", "type": "Secondary"}]}, "published": "2025-11-21T02:15:43.393", "references": [{"source": "[email protected]", "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"}], "sourceIdentifier": "[email protected]", "vulnStatus": "Awaiting Analysis", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-129"}], "source": "[email protected]", "type": "Primary"}]}

{"bugzilla": {"description": "vllm: vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs", "id": "2416280", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2416280"}, "csaw": false, "cvss3": {"cvss3_base_score": "6.5", "cvss3_scoring_vector": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H", "status": "draft"}, "cwe": "CWE-129", "details": ["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."], "mitigation": {"lang": "en:us", "value": "No mitigation is currently available that meets Red Hat Product Security\u2019s standards for usability, deployment, applicability, or stability."}, "name": "CVE-2025-62372", "package_state": [{"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaiis-preview/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaiis/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaiis/vllm-rocm-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaiis/vllm-spyre-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaiis/vllm-tpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-amd-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-aws-nvidia-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-azure-amd-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-azure-nvidia-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-gcp-nvidia-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-intel-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/bootc-nvidia-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/instructlab-amd-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/instructlab-intel-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Fix deferred", "package_name": "rhelai1/instructlab-nvidia-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Fix deferred", "package_name": "rhelai3/bootc-aws-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Fix deferred", "package_name": "rhelai3/bootc-azure-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Fix deferred", "package_name": "rhelai3/bootc-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Fix deferred", "package_name": "rhelai3/bootc-gcp-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-kserve-agent-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-kserve-controller-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-kserve-router-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-kserve-storage-initializer-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-vllm-cpu-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-vllm-cuda-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-vllm-gaudi-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-vllm-rocm-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}], "public_date": "2025-11-21T01:22:37Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2025-62372\nhttps://nvd.nist.gov/vuln/detail/CVE-2025-62372\nhttps://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b\nhttps://github.com/vllm-project/vllm/pull/27204\nhttps://github.com/vllm-project/vllm/pull/6613\nhttps://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw"], "statement": "This flaw is rated Moderate rather than Important because its impact is strictly limited to availability and requires low but existing privileges to exploit. The issue arises from incomplete shape validation of multimodal embedding tensors, which can cause deterministic crashes in the inference engine, but it does not enable memory corruption, data leakage, integrity compromise, or execution of arbitrary code. Exploitation requires an authenticated or API-key-holding user to submit malformed multimodal inputs, meaning it cannot be triggered by an unauthenticated attacker on an exposed endpoint. Additionally, the failure mode is a clean crash rather than undefined behavior, so the blast radius is constrained to service interruption rather than broader systemic compromise. These factors\u2014PR:L requirement, no confidentiality/integrity impact, deterministic failure mode, and scoped DoS only\u2014technically align the issue with Moderate severity instead of an Important flaw.", "threat_severity": "Moderate"}