CVE-2026-34755
Estado: ModificadaMedia (6.5)—
vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This vulnerability is fixed in 0.19.0.
CVSS
- Versión: 3.1
- Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- Puntuación base: 6.5
Probabilidad de explotación (EPSS)
- Probabilidad de explotación en los próximos 30 días: 0.84%
- Percentil entre todas las CVEs puntuadas: 57
- Fecha de la puntuación: 6/10/2026
EPSS (Exploit Prediction Scoring System, de FIRST) estima la probabilidad de que una vulnerabilidad sea explotada en 30 días. Complementa a CVSS (impacto) y a CISA KEV (explotación confirmada).
Tecnologías afectadas (1)
CWE
- CWE-770
- CWE-770
Referencias
- https://github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p
- https://access.redhat.com/errata/RHSA-2026:36005
- https://access.redhat.com/errata/RHSA-2026:36006
- https://access.redhat.com/errata/RHSA-2026:57380
- https://access.redhat.com/errata/RHSA-2026:57387
- https://access.redhat.com/errata/RHSA-2026:57389
- https://access.redhat.com/errata/RHSA-2026:57390
- https://access.redhat.com/errata/RHSA-2026:59144
- https://access.redhat.com/errata/RHSA-2026:59151
- https://access.redhat.com/security/cve/CVE-2026-34755
- https://bugzilla.redhat.com/show_bug.cgi?id=2455403
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34755.json
JSON original (NVD)
Mostrar
{
"id": "CVE-2026-34755",
"cveTags": [],
"metrics": {
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-34755",
"role": "CISA Coordinator",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"version": "2.0.3",
"timestamp": "2026-04-06T18:36:13.854345Z"
}
}
],
"cvssMetricV31": [
{
"type": "Secondary",
"source": "security-advisories@github.com",
"cvssData": {
"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"
},
"impactScore": 3.6,
"exploitabilityScore": 2.8
},
{
"type": "Secondary",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c",
"cvssData": {
"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"
},
"impactScore": 3.6,
"exploitabilityScore": 2.8
}
]
},
"affected": [
{
"source": "security-advisories@github.com",
"affectedData": [
{
"vendor": "vllm-project",
"product": "vllm",
"versions": [
{
"status": "affected",
"version": ">= 0.7.0, < 0.19.0"
}
]
}
]
},
{
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c",
"affectedData": [
{
"cpes": [
"cpe:/a:redhat:ai_inference_server:3.2::el9"
],
"vendor": "Red Hat",
"product": "Red Hat AI Inference Server 3.2",
"versions": [
{
"status": "unaffected",
"version": "1782951012",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhaiis/vllm-cuda-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:ai_inference_server:3.2::el9"
],
"vendor": "Red Hat",
"product": "Red Hat AI Inference Server 3.2",
"versions": [
{
"status": "unaffected",
"version": "1782951244",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhaiis/vllm-rocm-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:ai_inference_server:3.4::el9"
],
"vendor": "Red Hat",
"product": "Red Hat AI Inference Server 3.4",
"versions": [
{
"status": "unaffected",
"version": "1787151769",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhaii/vllm-cpu-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:ai_inference_server:3.4::el9"
],
"vendor": "Red Hat",
"product": "Red Hat AI Inference Server 3.4",
"versions": [
{
"status": "unaffected",
"version": "1787151840",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhaii/vllm-spyre-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:ai_inference_server:3.4::el9"
],
"vendor": "Red Hat",
"product": "Red Hat AI Inference Server 3.4",
"versions": [
{
"status": "unaffected",
"version": "1787151771",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhaii/vllm-cuda-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:ai_inference_server:3.4::el9"
],
"vendor": "Red Hat",
"product": "Red Hat AI Inference Server 3.4",
"versions": [
{
"status": "unaffected",
"version": "1787151774",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhaii/vllm-rocm-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:enterprise_linux_ai:3.4::el9"
],
"vendor": "Red Hat",
"product": "Red Hat Enterprise Linux AI 3.4",
"versions": [
{
"status": "unaffected",
"version": "1787310717",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhelai3/disk-image-cuda-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:enterprise_linux_ai:3.4::el9"
],
"vendor": "Red Hat",
"product": "Red Hat Enterprise Linux AI 3.4",
"versions": [
{
"status": "unaffected",
"version": "1787253912",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhelai3/bootc-aws-cuda-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:enterprise_linux_ai:3.4::el9"
],
"vendor": "Red Hat",
"product": "Red Hat Enterprise Linux AI 3.4",
"versions": [
{
"status": "unaffected",
"version": "1787253989",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhelai3/bootc-azure-cuda-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:enterprise_linux_ai:3.4::el9"
],
"vendor": "Red Hat",
"product": "Red Hat Enterprise Linux AI 3.4",
"versions": [
{
"status": "unaffected",
"version": "1787254059",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhelai3/bootc-azure-rocm-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:enterprise_linux_ai:3.4::el9"
],
"vendor": "Red Hat",
"product": "Red Hat Enterprise Linux AI 3.4",
"versions": [
{
"status": "unaffected",
"version": "1787243961",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhelai3/bootc-cuda-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:enterprise_linux_ai:3.4::el9"
],
"vendor": "Red Hat",
"product": "Red Hat Enterprise Linux AI 3.4",
"versions": [
{
"status": "unaffected",
"version": "1787253774",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhelai3/bootc-gcp-cuda-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:enterprise_linux_ai:3.4::el9"
],
"vendor": "Red Hat",
"product": "Red Hat Enterprise Linux AI 3.4",
"versions": [
{
"status": "unaffected",
"version": "1787244006",
"lessThan": "*",
"versionType": "rpm"
}
],
"packageName": "rhelai3/bootc-rocm-rhel9",
"collectionURL": "https://catalog.redhat.com/software/containers/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:ai_inference_server:3"
],
"vendor": "Red Hat",
"product": "Red Hat AI Inference Server",
"packageName": "rhaiis/vllm-neuron-rhel9",
"collectionURL": "https://access.redhat.com/downloads/content/package-browser/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:ai_inference_server:3"
],
"vendor": "Red Hat",
"product": "Red Hat AI Inference Server",
"packageName": "rhaiis/vllm-tpu-rhel9",
"collectionURL": "https://access.redhat.com/downloads/content/package-browser/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:openshift_ai"
],
"vendor": "Red Hat",
"product": "Red Hat OpenShift AI (RHOAI)",
"packageName": "rhoai/odh-kserve-agent-rhel9",
"collectionURL": "https://access.redhat.com/downloads/content/package-browser/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:openshift_ai"
],
"vendor": "Red Hat",
"product": "Red Hat OpenShift AI (RHOAI)",
"packageName": "rhoai/odh-kserve-controller-rhel9",
"collectionURL": "https://access.redhat.com/downloads/content/package-browser/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:openshift_ai"
],
"vendor": "Red Hat",
"product": "Red Hat OpenShift AI (RHOAI)",
"packageName": "rhoai/odh-kserve-router-rhel9",
"collectionURL": "https://access.redhat.com/downloads/content/package-browser/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:openshift_ai"
],
"vendor": "Red Hat",
"product": "Red Hat OpenShift AI (RHOAI)",
"packageName": "rhoai/odh-kserve-storage-initializer-rhel9",
"collectionURL": "https://access.redhat.com/downloads/content/package-browser/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:openshift_ai"
],
"vendor": "Red Hat",
"product": "Red Hat OpenShift AI (RHOAI)",
"packageName": "rhoai/odh-vllm-cpu-rhel9",
"collectionURL": "https://access.redhat.com/downloads/content/package-browser/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:openshift_ai"
],
"vendor": "Red Hat",
"product": "Red Hat OpenShift AI (RHOAI)",
"packageName": "rhoai/odh-vllm-cuda-rhel9",
"collectionURL": "https://access.redhat.com/downloads/content/package-browser/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:openshift_ai"
],
"vendor": "Red Hat",
"product": "Red Hat OpenShift AI (RHOAI)",
"packageName": "rhoai/odh-vllm-gaudi-rhel9",
"collectionURL": "https://access.redhat.com/downloads/content/package-browser/",
"defaultStatus": "affected"
},
{
"cpes": [
"cpe:/a:redhat:openshift_ai"
],
"vendor": "Red Hat",
"product": "Red Hat OpenShift AI (RHOAI)",
"packageName": "rhoai/odh-vllm-rocm-rhel9",
"collectionURL": "https://access.redhat.com/downloads/content/package-browser/",
"defaultStatus": "affected"
}
]
}
],
"published": "2026-04-06T16:16:36.463",
"references": [
{
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p",
"tags": [
"Patch",
"Vendor Advisory"
],
"source": "security-advisories@github.com"
},
{
"url": "https://access.redhat.com/errata/RHSA-2026:36005",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c"
},
{
"url": "https://access.redhat.com/errata/RHSA-2026:36006",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c"
},
{
"url": "https://access.redhat.com/errata/RHSA-2026:57380",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c"
},
{
"url": "https://access.redhat.com/errata/RHSA-2026:57387",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c"
},
{
"url": "https://access.redhat.com/errata/RHSA-2026:57389",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c"
},
{
"url": "https://access.redhat.com/errata/RHSA-2026:57390",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c"
},
{
"url": "https://access.redhat.com/errata/RHSA-2026:59144",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c"
},
{
"url": "https://access.redhat.com/errata/RHSA-2026:59151",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c"
},
{
"url": "https://access.redhat.com/security/cve/CVE-2026-34755",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c"
},
{
"url": "https://bugzilla.redhat.com/show_bug.cgi?id=2455403",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c"
},
{
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34755.json",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c"
}
],
"vulnStatus": "Modified",
"weaknesses": [
{
"type": "Secondary",
"source": "security-advisories@github.com",
"description": [
{
"lang": "en",
"value": "CWE-770"
}
]
},
{
"type": "Secondary",
"source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c",
"description": [
{
"lang": "en",
"value": "CWE-770"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This vulnerability is fixed in 0.19.0."
}
],
"lastModified": "2026-08-25T13:18:39.240",
"configurations": [
{
"nodes": [
{
"negate": false,
"cpeMatch": [
{
"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"vulnerable": true,
"matchCriteriaId": "36E450C9-1DE7-4CEE-835B-FBE1D9F37704",
"versionEndExcluding": "0.19.0",
"versionStartIncluding": "0.7.0"
}
],
"operator": "OR"
}
]
}
],
"sourceIdentifier": "security-advisories@github.com"
}