CVE-2026-53923

{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-53923", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2026-06-11T15:46:12.316Z", "datePublished": "2026-06-22T21:55:42.001Z", "dateUpdated": "2026-06-23T15:05:21.711Z"}, "containers": {"cna": {"title": "vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow", "problemTypes": [{"descriptions": [{"cweId": "CWE-681", "lang": "en", "description": "CWE-681: Incorrect Conversion between Numeric Types", "type": "CWE"}]}, {"descriptions": [{"cweId": "CWE-200", "lang": "en", "description": "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor", "type": "CWE"}]}], "metrics": [{"cvssV4_0": {"attackVector": "NETWORK", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "userInteraction": "PASSIVE", "vulnConfidentialityImpact": "LOW", "vulnIntegrityImpact": "LOW", "vulnAvailabilityImpact": "NONE", "subConfidentialityImpact": "NONE", "subIntegrityImpact": "NONE", "subAvailabilityImpact": "NONE", "baseScore": 5.3, "baseSeverity": "MEDIUM", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N", "version": "4.0"}}], "references": [{"name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4"}, {"name": "https://github.com/vllm-project/vllm/pull/44971", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/44971"}, {"name": "https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e"}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"version": ">= 0.5.5, < 0.23.1rc0", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-06-22T21:55:42.001Z"}, "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models (LLMs). From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels (csrc/quantization/gguf/gguf_kernel.cu) causes partial tensor processing. The output tensor is allocated at full size via torch::empty (uninitialized memory), but the dequantize CUDA kernel processes only a truncated number of elements. The unfilled portion of the output tensor retains whatever was previously in GPU memory. In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure. This vulnerability is fixed in 0.23.1rc0."}], "source": {"advisory": "GHSA-5jv2-g5wq-cmr4", "discovery": "UNKNOWN"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-06-23T15:04:15.555317Z", "id": "CVE-2026-53923", "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": "2026-06-23T15:05:21.711Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-53923", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2026-06-23T15:04:15.555317Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-06-23T15:04:19.969Z"}}], "cna": {"title": "vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow", "source": {"advisory": "GHSA-5jv2-g5wq-cmr4", "discovery": "UNKNOWN"}, "metrics": [{"cvssV4_0": {"version": "4.0", "baseScore": 5.3, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N", "userInteraction": "PASSIVE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "LOW", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "NONE", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "LOW"}}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"status": "affected", "version": ">= 0.5.5, < 0.23.1rc0"}]}], "references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4", "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4", "tags": ["x_refsource_CONFIRM"]}, {"url": "https://github.com/vllm-project/vllm/pull/44971", "name": "https://github.com/vllm-project/vllm/pull/44971", "tags": ["x_refsource_MISC"]}, {"url": "https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e", "name": "https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e", "tags": ["x_refsource_MISC"]}], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models (LLMs). From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels (csrc/quantization/gguf/gguf_kernel.cu) causes partial tensor processing. The output tensor is allocated at full size via torch::empty (uninitialized memory), but the dequantize CUDA kernel processes only a truncated number of elements. The unfilled portion of the output tensor retains whatever was previously in GPU memory. In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure. This vulnerability is fixed in 0.23.1rc0."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-681", "description": "CWE-681: Incorrect Conversion between Numeric Types"}]}, {"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-200", "description": "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-06-22T21:55:42.001Z"}}}, "cveMetadata": {"cveId": "CVE-2026-53923", "state": "PUBLISHED", "dateUpdated": "2026-06-23T15:05:21.711Z", "dateReserved": "2026-06-11T15:46:12.316Z", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "datePublished": "2026-06-22T21:55:42.001Z", "assignerShortName": "GitHub_M"}, "dataVersion": "5.2"}

{"affected": [{"affectedData": [{"product": "vllm", "vendor": "vllm-project", "versions": [{"status": "affected", "version": ">= 0.5.5, < 0.23.1rc0"}]}], "source": "security-advisories@github.com"}], "configurations": [{"nodes": [{"cpeMatch": [{"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "matchCriteriaId": "EC2E4E13-D3B7-4A9F-AF31-A9CD7753B6F4", "versionEndExcluding": "0.23.1", "versionStartIncluding": "0.5.5", "vulnerable": true}], "negate": false, "operator": "OR"}]}], "cveTags": [], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models (LLMs). From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels (csrc/quantization/gguf/gguf_kernel.cu) causes partial tensor processing. The output tensor is allocated at full size via torch::empty (uninitialized memory), but the dequantize CUDA kernel processes only a truncated number of elements. The unfilled portion of the output tensor retains whatever was previously in GPU memory. In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure. This vulnerability is fixed in 0.23.1rc0."}, {"lang": "es", "value": "vLLM es un motor de inferencia y servicio para modelos de lenguaje grandes (LLM). Desde 0.5.5 hasta 0.23.1rc0, la truncaci\u00f3n de enteros de las dimensiones del tensor en los kernels de desquantificaci\u00f3n GGUF de vLLM (csrc/quantization/gguf/gguf_kernel.cu) provoca un procesamiento parcial del tensor. El tensor de salida se asigna a tama\u00f1o completo mediante torch::empty (memoria no inicializada), pero el kernel CUDA de desquantificaci\u00f3n procesa solo un n\u00famero truncado de elementos. La porci\u00f3n no rellenada del tensor de salida retiene lo que estuviera previamente en la memoria de la GPU. En implementaciones de inferencia multiusuario, esta memoria residual de la GPU puede contener datos de tensor de solicitudes de inferencia de otros usuarios, lo que constituye una revelaci\u00f3n de informaci\u00f3n. Esta vulnerabilidad se corrige en 0.23.1rc0."}], "id": "CVE-2026-53923", "lastModified": "2026-10-25T23:10:00.167", "metrics": {"cvssMetricV31": [{"cvssData": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "NONE", "baseScore": 7.5, "baseSeverity": "HIGH", "confidentialityImpact": "HIGH", "integrityImpact": "NONE", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N", "version": "3.1"}, "exploitabilityScore": 3.9, "impactScore": 3.6, "source": "nvd@nist.gov", "type": "Primary"}], "cvssMetricV40": [{"cvssData": {"Automatable": "NOT_DEFINED", "Recovery": "NOT_DEFINED", "Safety": "NOT_DEFINED", "attackComplexity": "LOW", "attackRequirements": "NONE", "attackVector": "NETWORK", "availabilityRequirement": "NOT_DEFINED", "baseScore": 5.3, "baseSeverity": "MEDIUM", "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": "NONE", "providerUrgency": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "subConfidentialityImpact": "NONE", "subIntegrityImpact": "NONE", "userInteraction": "PASSIVE", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N/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": "NONE", "vulnConfidentialityImpact": "LOW", "vulnIntegrityImpact": "LOW", "vulnerabilityResponseEffort": "NOT_DEFINED"}, "source": "security-advisories@github.com", "type": "Secondary"}], "ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-53923", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "role": "CISA Coordinator", "timestamp": "2026-06-23T15:04:15.555317Z", "version": "2.0.3"}}]}, "published": "2026-06-22T23:16:30.737", "references": [{"source": "security-advisories@github.com", "tags": ["Patch"], "url": "https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e"}, {"source": "security-advisories@github.com", "tags": ["Issue Tracking"], "url": "https://github.com/vllm-project/vllm/pull/44971"}, {"source": "security-advisories@github.com", "tags": ["Third Party Advisory"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Analyzed", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-200"}, {"lang": "en", "value": "CWE-681"}], "source": "security-advisories@github.com", "type": "Secondary"}]}

{"bugzilla": {"description": "vllm: vLLM: Information disclosure via integer truncation", "id": "2491579", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2491579"}, "csaw": false, "cvss3": {"cvss3_base_score": "4.3", "cvss3_scoring_vector": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N", "status": "draft"}, "cwe": "CWE-824", "details": ["vLLM is an inference and serving engine for large language models (LLMs). From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels (csrc/quantization/gguf/gguf_kernel.cu) causes partial tensor processing. The output tensor is allocated at full size via torch::empty (uninitialized memory), but the dequantize CUDA kernel processes only a truncated number of elements. The unfilled portion of the output tensor retains whatever was previously in GPU memory. In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure. This vulnerability is fixed in 0.23.1rc0.", "A flaw was found in vLLM. Integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels leads to partial tensor processing. This results in the output tensor retaining previously used GPU memory, which, in multi-tenant inference deployments, can expose sensitive tensor data from other users' requests. This constitutes an information disclosure vulnerability."], "mitigation": {"lang": "en:us", "value": "No mitigation is required for unaffected deployments. Restrict untrusted access to inference APIs as a general hardening measure."}, "name": "CVE-2026-53923", "package_state": [{"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaiis/vllm-cpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaiis/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaiis/vllm-neuron-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaiis/vllm-rocm-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaiis/vllm-spyre-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaiis/vllm-tpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaii/vllm-cpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaii/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaii/vllm-gaudi-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaii/vllm-neuron-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaii/vllm-rocm-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaii/vllm-spyre-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Not affected", "package_name": "rhaii/vllm-tpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Not affected", "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": "Not affected", "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": "Not affected", "package_name": "rhelai3/bootc-azure-rocm-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Not affected", "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": "Not affected", "package_name": "rhelai3/bootc-gaudi-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Not affected", "package_name": "rhelai3/bootc-gcp-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Not affected", "package_name": "rhelai3/bootc-rocm-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Not affected", "package_name": "rhoai/odh-kserve-agent-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Not affected", "package_name": "rhoai/odh-kserve-controller-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Not affected", "package_name": "rhoai/odh-kserve-router-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Not affected", "package_name": "rhoai/odh-kserve-storage-initializer-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Not affected", "package_name": "rhoai/odh-llm-d-kv-cache-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Not affected", "package_name": "rhoai/odh-vllm-gaudi-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}], "public_date": "2026-06-22T21:55:42Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2026-53923\nhttps://nvd.nist.gov/vuln/detail/CVE-2026-53923\nhttps://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e\nhttps://github.com/vllm-project/vllm/pull/44971\nhttps://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4"], "statement": "Red Hat rates this issue as having Low impact for Red Hat AI products. The upstream issue is limited information disclosure via integer truncation in vLLM sampling parameters. Red Hat OpenShift AI, Red Hat AI Inference Server, and Red Hat Enterprise Linux AI images are not considered affected because untrusted clients cannot control the vulnerable parameters in supported deployment models.", "threat_severity": "Low"}

{"affected": [{"configurations": [{"platform": null, "status": "affected", "versions": {"scheme": "generic", "value": "[0.5.5,0.23.1rc0)"}}], "enrichment": {"confidence": 100.0, "confidence_source": "matching", "scores": [{"score": 100.0, "source": "matching"}]}, "original": {"product": "vllm", "source": "cna", "vendor": "vllm-project"}, "product": "vllm", "vendor": "vllm-project"}], "created": "2026-06-22T23:30:05.607643+00:00", "updated": "2026-06-29T14:30:18.569642+00:00", "vendors": ["vllm-project", "vllm-project$PRODUCT$vllm"]}