{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-115916", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2026-10-23T20:21:45.107Z", "datePublished": "2026-10-26T17:18:17.582Z", "dateUpdated": "2026-11-02T17:50:28.478Z"}, "containers": {"cna": {"title": "vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)", "problemTypes": [{"descriptions": [{"cweId": "CWE-129", "lang": "en", "description": "CWE-129: Improper Validation of Array Index", "type": "CWE"}]}, {"descriptions": [{"cweId": "CWE-193", "lang": "en", "description": "CWE-193: Off-by-one Error", "type": "CWE"}]}], "metrics": [{"cvssV3_1": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 6.5, "baseSeverity": "MEDIUM", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "privilegesRequired": "LOW", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H", "version": "3.1"}}], "references": [{"name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4"}, {"name": "https://github.com/vllm-project/vllm/pull/59491", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/59491"}, {"name": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229"}, {"name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"version": "< 0.32.0", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-10-26T17:18:17.582Z"}, "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0."}], "source": {"advisory": "GHSA-q97c-p368-75c4", "discovery": "UNKNOWN"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-11-02T17:49:45.650631Z", "id": "CVE-2026-115916", "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": "2026-11-02T17:50:28.478Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-115916", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2026-11-02T17:49:45.650631Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-11-02T17:49:57.747Z"}}], "cna": {"title": "vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)", "source": {"advisory": "GHSA-q97c-p368-75c4", "discovery": "UNKNOWN"}, "metrics": [{"cvssV3_1": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 6.5, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "LOW", "confidentialityImpact": "NONE"}}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"status": "affected", "version": "< 0.32.0"}]}], "references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4", "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4", "tags": ["x_refsource_CONFIRM"]}, {"url": "https://github.com/vllm-project/vllm/pull/59491", "name": "https://github.com/vllm-project/vllm/pull/59491", "tags": ["x_refsource_MISC"]}, {"url": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229", "name": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229", "tags": ["x_refsource_MISC"]}, {"url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0", "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0", "tags": ["x_refsource_MISC"]}], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-129", "description": "CWE-129: Improper Validation of Array Index"}]}, {"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-193", "description": "CWE-193: Off-by-one Error"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-10-26T17:18:17.582Z"}}}, "cveMetadata": {"cveId": "CVE-2026-115916", "state": "PUBLISHED", "dateUpdated": "2026-11-02T17:50:28.478Z", "dateReserved": "2026-10-23T20:21:45.107Z", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "datePublished": "2026-10-26T17:18:17.582Z", "assignerShortName": "GitHub_M"}, "dataVersion": "5.2"}

{"affected": [{"affectedData": [{"product": "vllm", "vendor": "vllm-project", "versions": [{"status": "affected", "version": "< 0.32.0"}]}], "source": "security-advisories@github.com"}], "configurations": [{"nodes": [{"cpeMatch": [{"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "matchCriteriaId": "F7BDDF1C-9078-4F18-A972-846C4C1363E5", "versionEndExcluding": "0.32.0", "vulnerable": true}], "negate": false, "operator": "OR"}]}], "cveTags": [], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0."}], "id": "CVE-2026-115916", "lastModified": "2026-11-02T18:18:39.033", "metrics": {"cvssMetricV31": [{"cvssData": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 6.5, "baseSeverity": "MEDIUM", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "privilegesRequired": "LOW", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H", "version": "3.1"}, "exploitabilityScore": 2.8, "impactScore": 3.6, "source": "security-advisories@github.com", "type": "Secondary"}], "ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-115916", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "role": "CISA Coordinator", "timestamp": "2026-11-02T17:49:45.650631Z", "version": "2.0.3"}}]}, "published": "2026-10-26T18:17:39.080", "references": [{"source": "security-advisories@github.com", "tags": ["Patch"], "url": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229"}, {"source": "security-advisories@github.com", "tags": ["Patch"], "url": "https://github.com/vllm-project/vllm/pull/59491"}, {"source": "security-advisories@github.com", "tags": ["Release Notes"], "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"}, {"source": "security-advisories@github.com", "tags": ["Patch", "Vendor Advisory"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Analyzed", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-129"}, {"lang": "en", "value": "CWE-193"}], "source": "security-advisories@github.com", "type": "Secondary"}]}

{"bugzilla": {"description": "vllm: vLLM: Denial of Service via out-of-bounds prompt token ID", "id": "2560972", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2560972"}, "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-193", "details": ["A flaw was found in vLLM. This vulnerability allows a remote attacker to cause a Denial of Service (DoS) by submitting a request containing an out-of-bounds pre-tokenized prompt token identifier. Due to an off-by-one error in input validation, an invalid token identifier equal to the vocabulary size is accepted, which triggers an assertion failure during embedding processing and terminates the inference engine."], "name": "CVE-2026-115916", "package_state": [{"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-cpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-gaudi-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-neuron-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-omni-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-rocm-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-spyre-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii-fast/vllm-tpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-cpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-gaudi-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-neuron-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-rocm-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-spyre-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaii/vllm-tpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"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-azure-rocm-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-gaudi-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:enterprise_linux_ai:3", "fix_state": "Fix deferred", "package_name": "rhelai3/bootc-rocm-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-llm-d-kv-cache-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Fix deferred", "package_name": "rhoai/odh-th-torch-cuda-py312-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": "2026-10-26T17:18:17Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2026-115916\nhttps://nvd.nist.gov/vuln/detail/CVE-2026-115916\nhttps://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229\nhttps://github.com/vllm-project/vllm/pull/59491\nhttps://github.com/vllm-project/vllm/releases/tag/v0.32.0\nhttps://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4"], "threat_severity": "Moderate"}