{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-69147", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2026-08-03T15:20:30.218Z", "datePublished": "2026-09-16T17:49:20.427Z", "dateUpdated": "2026-09-16T18:37:14.118Z"}, "containers": {"cna": {"title": "vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation", "problemTypes": [{"descriptions": [{"cweId": "CWE-400", "lang": "en", "description": "CWE-400: Uncontrolled Resource Consumption", "type": "CWE"}]}, {"descriptions": [{"cweId": "CWE-770", "lang": "en", "description": "CWE-770: Allocation of Resources Without Limits or Throttling", "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-8pw2-6jv3-mj5j", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j"}, {"name": "https://github.com/vllm-project/vllm/pull/47259", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/47259"}, {"name": "https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda"}, {"name": "https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d"}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"version": "< 0.28.0", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-09-16T17:49:20.427Z"}, "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards that choice to VideoMediaIO even when startup configuration selected a software decoder. The engine's _reserve_mm_ipc_gpu_memory logic budgets decoder memory only from static configuration, so the request-selected VIDEO_LOADER_REGISTRY backend can create a CUDA context, decoder surfaces, and decoded-frame allocations that were not removed from the engine's KV-cache budget. An attacker able to submit video requests to a video-capable GPU deployment with PyNvVideoCodec installed can exhaust shared GPU memory, causing request failures, worker crashes, or denial of service. The first release containing the fix is version 0.28.0."}], "source": {"advisory": "GHSA-8pw2-6jv3-mj5j", "discovery": "UNKNOWN"}}, "adp": [{"references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j", "tags": ["exploit"]}], "metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-09-16T18:37:08.090589Z", "id": "CVE-2026-69147", "options": [{"Exploitation": "poc"}, {"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": "2026-09-16T18:37:14.118Z"}}]}}

{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-69147", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2026-08-03T15:20:30.218Z", "datePublished": "2026-09-16T17:49:20.427Z", "dateUpdated": "2026-09-16T18:37:14.118Z"}, "containers": {"cna": {"title": "vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation", "problemTypes": [{"descriptions": [{"cweId": "CWE-400", "lang": "en", "description": "CWE-400: Uncontrolled Resource Consumption", "type": "CWE"}]}, {"descriptions": [{"cweId": "CWE-770", "lang": "en", "description": "CWE-770: Allocation of Resources Without Limits or Throttling", "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-8pw2-6jv3-mj5j", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j"}, {"name": "https://github.com/vllm-project/vllm/pull/47259", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/47259"}, {"name": "https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda"}, {"name": "https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d"}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"version": "< 0.28.0", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-09-16T17:49:20.427Z"}, "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards that choice to VideoMediaIO even when startup configuration selected a software decoder. The engine's _reserve_mm_ipc_gpu_memory logic budgets decoder memory only from static configuration, so the request-selected VIDEO_LOADER_REGISTRY backend can create a CUDA context, decoder surfaces, and decoded-frame allocations that were not removed from the engine's KV-cache budget. An attacker able to submit video requests to a video-capable GPU deployment with PyNvVideoCodec installed can exhaust shared GPU memory, causing request failures, worker crashes, or denial of service. The first release containing the fix is version 0.28.0."}], "source": {"advisory": "GHSA-8pw2-6jv3-mj5j", "discovery": "UNKNOWN"}}, "adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-69147", "role": "CISA Coordinator", "options": [{"Exploitation": "poc"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2026-09-16T18:37:08.090589Z"}}}], "references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j", "tags": ["exploit"]}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-09-16T18:36:52.431Z"}}]}}

{"affected": [{"affectedData": [{"product": "vllm", "vendor": "vllm-project", "versions": [{"status": "affected", "version": "< 0.28.0"}]}], "source": "security-advisories@github.com"}], "configurations": [{"nodes": [{"cpeMatch": [{"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "matchCriteriaId": "348E22A1-F884-4209-9464-6ACE00818B2F", "versionEndExcluding": "0.28.0", "vulnerable": true}], "negate": false, "operator": "OR"}]}], "cveTags": [], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards that choice to VideoMediaIO even when startup configuration selected a software decoder. The engine's _reserve_mm_ipc_gpu_memory logic budgets decoder memory only from static configuration, so the request-selected VIDEO_LOADER_REGISTRY backend can create a CUDA context, decoder surfaces, and decoded-frame allocations that were not removed from the engine's KV-cache budget. An attacker able to submit video requests to a video-capable GPU deployment with PyNvVideoCodec installed can exhaust shared GPU memory, causing request failures, worker crashes, or denial of service. The first release containing the fix is version 0.28.0."}], "id": "CVE-2026-69147", "lastModified": "2026-10-07T14:16:57.827", "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-2026-69147", "options": [{"exploitation": "poc"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "role": "CISA Coordinator", "timestamp": "2026-09-16T18:37:08.090589Z", "version": "2.0.3"}}]}, "published": "2026-09-16T18:17:11.770", "references": [{"source": "security-advisories@github.com", "tags": ["Patch"], "url": "https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda"}, {"source": "security-advisories@github.com", "tags": ["Patch"], "url": "https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d"}, {"source": "security-advisories@github.com", "tags": ["Issue Tracking", "Patch"], "url": "https://github.com/vllm-project/vllm/pull/47259"}, {"source": "security-advisories@github.com", "tags": ["Exploit", "Vendor Advisory"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j"}, {"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "tags": ["Exploit", "Vendor Advisory"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Analyzed", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-400"}, {"lang": "en", "value": "CWE-770"}], "source": "security-advisories@github.com", "type": "Secondary"}]}

{"bugzilla": {"description": "vllm: vLLM: GPU memory exhaustion via PyNvVideoCodec decode bypass", "id": "2535581", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2535581"}, "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-770", "details": ["A flaw was found in vLLM, an inference and serving engine for large language models. An attacker can exploit this by submitting specially crafted video requests that force the use of the PyNvVideoCodec GPU decoder. This bypasses the engine's static GPU memory reservation, allowing the attacker to exhaust shared GPU memory. The consequence is a denial of service (DoS), leading to request failures or worker crashes."], "name": "CVE-2026-69147", "package_state": [{"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Fix deferred", "package_name": "rhaiis/vllm-cpu-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-neuron-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: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-gaudi-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}], "public_date": "2026-09-16T17:49:20Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2026-69147\nhttps://nvd.nist.gov/vuln/detail/CVE-2026-69147\nhttps://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda\nhttps://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d\nhttps://github.com/vllm-project/vllm/pull/47259\nhttps://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j"], "threat_severity": "Moderate"}