vLLM Affected by Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing
vllm-project · vllm
Official source article: GitHub GHSA-PQ5C-RJHQ-QP7P ↗. Check the applicable product and release in the original source.
6.5MediumCVSS 3.1
Recommended action
Scheduled
Medium technical severity with no CISA KEV confirmation; remediate through the normal risk-based patch cycle unless local exposure raises the priority.
These OSV and GitHub advisory ranges apply only to the named package and ecosystem. A listed fixed version is not a universal product patch or proof that an update is installed.
Structured product status and remediation from the issuing vendor. Product-state explanations are always visible; large lists can be searched or downloaded.
1 current
CVE-2026-34755 · CSAF 2.0 · revision 3 · finalRed Hat Product SecurityvLLM: vLLM: Denial of Service due to excessive video frame processing
10 known affected
The vendor explicitly identifies these products as affected by this CVE.
rhaiis/vllm-neuron-rhel9 as a component of Red Hat AI Inference Server
rhaiis/vllm-tpu-rhel9 as a component of Red Hat AI Inference Server
rhoai/odh-kserve-agent-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
rhoai/odh-kserve-controller-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
rhoai/odh-kserve-router-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
rhoai/odh-kserve-storage-initializer-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
rhoai/odh-vllm-cpu-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
rhoai/odh-vllm-cuda-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
rhoai/odh-vllm-gaudi-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
rhoai/odh-vllm-rocm-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
Summary
A flaw was found in vLLM, an inference and serving engine for large language models. A remote attacker can exploit a vulnerability in the VideoMediaIO.load_base64() method by sending a single API request containing a large number of comma-separated base64-encoded JPEG frames. This bypasses the intended frame count limit, causing the server to decode all frames into memory. This can lead to an Out-of-Memory (OOM) crash, resulting in a Denial of Service (DoS) for the affected system.
Remediation
For more information visit https://access.redhat.com/errata/RHSA-2026:36005
Optional official sources
National CERT insights ?CERT means Computer Emergency Response Team; CSIRT is the closely related term Computer Security Incident Response Team.
Choose official national sources for this report. Each advisory shows its original language. Your selection is remembered on this device and included in shared links.
Official European source
ENISA European Vulnerability Database
Official EUVD identifiers, advisory evidence and known-exploited context. Missing fields are not treated as evidence of low risk.
1 current
ENISA EUVD identifier
EUVD-2026-19350
No EUVD known-exploited evidence
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.
EUVD state
Present in the current official mapping
Known exploitation
Not present in the current ENISA EUVD known-exploited dataset. This is not proof of no exploitation.
ENISA score
6.5 · CVSS 3.1
Advisory evidence
No linked advisory details stored yet
Recommended actionScheduled
Medium technical severity with no CISA KEV confirmation; remediate through the normal risk-based patch cycle unless local exposure raises the priority.
Patch available
01
What, why and how
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.
What
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.
Why
The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.
How
An attacker operating through a network path may attempt exploitation with low privileges. If successful, the issue may disrupt the affected service.
What
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.
Why
The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.
How
An attacker operating through a network path may attempt exploitation with low privileges. If successful, the issue may disrupt the affected service.
02
Exploit reality and attack path
CVSS severity, EPSS forecast probability, public exploit material and CISA-confirmed exploitation are separate signals.
Observed exploitation ?Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.No confirmed evidence
No CISA KEV match was present at the last successful refresh. This means no confirmation from that source, not proof of no exploitation.
Public PoC / exploit material ?Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.None recorded
No exploit-tagged reference or CISA SSVC proof-of-concept state is currently recorded. Research may still exist outside the structured feeds.
Likely attack path
a network path → Allocation of Resources Without Limits or Throttling → disrupt the affected service
Attack surface
Network
Privileges required
Low: a basic authenticated account is required
User interaction
None
Attack complexity
Low: no specialised conditions are recorded
Security boundary
Unchanged: impact remains within the vulnerable component's security authority
Weakness ?CWE means Common Weakness Enumeration: a standard category for the underlying weakness.
CWE-770: Allocation of Resources Without Limits or Throttling. The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.
CVSS vector ?CVSS means Common Vulnerability Scoring System. The vector records the metric values used to calculate technical severity.
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Common Vulnerability Scoring System 3.1: the compact vector below is decoded into plain language.
AVNetworkAttack vector: The vulnerable component can be reached over a network.ACLowAttack complexity: No specialised conditions are required beyond attacker-controlled input.PRLowPrivileges required: The attacker needs basic user-level privileges.UINoneUser interaction: No action by another user is required.SUnchangedScope: The security impact remains within the vulnerable component's authority.CNoneConfidentiality impact: No direct loss is represented by this metric.INoneIntegrity impact: No direct loss is represented by this metric.AHighAvailability impact: A successful attack can cause a major loss.
Post-exploitation / living off the land
No specific living-off-the-land technique is confirmed in the structured sources. Monitor normal administration tools for activity inconsistent with the affected service's baseline.
NetworkDenial of serviceCWE-770
A
Official authority intelligence
Only matched European and national findings are included. Language selectors and unavailable sources are omitted.
ENISA EUVD · EUVD-2026-19350Official EUVD mapping
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.
Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Dateien zu manipulieren, Sicherheitsmaßnahmen zu umgehen, vertrauliche Informationen offenzulegen oder einen Denial-of-Service-Zustand herbeizuführen.
Official advisory ↗JVN iPedia · Japanese · JVNDB-2026-011965vLLMにおける制限またはスロットリング無しのリソースの割り当てに関する脆弱性
Operational remediation based on structured source evidence.
Status ?Patch availability is based on structured fixed-version fields and authoritative update references. If no fix is verified, check the vendor advisory before making a change.
For more information visit https://access.redhat.com/errata/RHSA-2026:36005
Workaround
No verified workaround is recorded. If business-safe, reduce exposure to the affected interface and allow only trusted sources until authoritative guidance is available.
04
Evidence and provenance
Published 6 Apr 2026 · Last source change 25 Aug 2026, 12:05 UTC · CWE-770 · Allocation of Resources Without Limits or Throttling
CVE recordCVE.org · 5.2
CVSS sourceCNA
EPSS source ?The date BlackTree first stored a score for this CVE from the daily FIRST EPSS feed.FIRST · tracked since 2026-08-14
European sourceENISA EUVD · EUVD-2026-19350
Product sourceVendor CSAF · Red Hat Product Security
Remediation sourceVendor CSAF · Red Hat Product Security
CWE sourceCNA
NVD statusNVD modified after enrichment
Core structured fields are present and their contributing authorities are shown above.
Affected versionsThe structured affected or fixed version information changed.
Before
>= 0.7.0, < 0.19.0 · Fixed: An authoritative update reference is available, but the fixed version is not recorded in the structured CVE fields. Check the linked vendor advisory for the applicable release.
After
>= 0.7.0, < 0.19.0 · Fixed: For more information visit https://access.redhat.com/errata/RHSA-2026:36005
Affected versionsThe structured affected or fixed version information changed.
Before
rhaiis/vllm-neuron-rhel9 as a component of Red Hat AI Inference Server; rhaiis/vllm-tpu-rhel9 as a component of Red Hat AI Inference Server; rhelai3/bootc-aws-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-azure-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-azure-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-gcp-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhoai/odh-kserve-agent-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-kserve-controller-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-kserve-router-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-kserve-storage-initializer-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-vllm-cpu-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-vllm-cuda-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-vllm-gaudi-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-vllm-rocm-rhel9 as a component of Red Hat OpenShift AI (RHOAI) · Fixed: registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:6b93986199cc8e02e9672374938a2aac7b7452d1bf7d1a8a6445bfe1940f6328_amd64 as a component of Red Hat AI Inference Server 3.2; registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:9533230dd9b2ab392c96f4e8a556ddbebf0be308befdf92691dc7e228da361bf_arm64 as a component of Red Hat AI Inference Server 3.2; registry.redhat.io/rhaiis/vllm-rocm-rhel9@sha256:7e61f6b8bbdf8c1e0b04de9ee6cfe0b6ff493a5bd4ad5dc52de2c308d2389d0f_amd64 as a component of Red Hat AI Inference Server 3.2; registry.redhat.io/rhaii/vllm-cpu-rhel9@sha256:2e9fee8758cfe000f5b304c3de525fc812433fc2ad39122de86140f36c7be04f_amd64 as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhaii/vllm-cuda-rhel9@sha256:5da7a63ad71f6d047a35bfbd572a141be894bae84e60a2b22a237116c477a248_arm64 as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhaii/vllm-cuda-rhel9@sha256:d2ed07d307845135c089bc7644b64734b9349d517abf746c9aa0aa23ed263da5_amd64 as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhaii/vllm-rocm-rhel9@sha256:eb2ca896461f782d8c4c239d36545a1a749d17bebd9fdc0652024092614c69c2_amd64 as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhaii/vllm-spyre-rhel9@sha256:3657354eb0edeb7e0e9aad2a434d7f264626b3d906f4e3e8502a95a73772ca41_s390x as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhaii/vllm-spyre-rhel9@sha256:54ad323a1a44f99991ca9d28cf0a364a44c5bbce143891936f6c668612c3ffb0_amd64 as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhaii/vllm-spyre-rhel9@sha256:b35ecb302c7f4e270f44bf70b7f7f8d053eb74761b1104fea346af9a8e089d09_ppc64le as a component of Red Hat AI Inference Server 3.4
After
rhaiis/vllm-neuron-rhel9 as a component of Red Hat AI Inference Server; rhaiis/vllm-tpu-rhel9 as a component of Red Hat AI Inference Server; rhoai/odh-kserve-agent-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-kserve-controller-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-kserve-router-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-kserve-storage-initializer-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-vllm-cpu-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-vllm-cuda-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-vllm-gaudi-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-vllm-rocm-rhel9 as a component of Red Hat OpenShift AI (RHOAI) · Fixed: registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:6b93986199cc8e02e9672374938a2aac7b7452d1bf7d1a8a6445bfe1940f6328_amd64 as a component of Red Hat AI Inference Server 3.2; registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:9533230dd9b2ab392c96f4e8a556ddbebf0be308befdf92691dc7e228da361bf_arm64 as a component of Red Hat AI Inference Server 3.2; registry.redhat.io/rhaiis/vllm-rocm-rhel9@sha256:7e61f6b8bbdf8c1e0b04de9ee6cfe0b6ff493a5bd4ad5dc52de2c308d2389d0f_amd64 as a component of Red Hat AI Inference Server 3.2; registry.redhat.io/rhaii/vllm-cpu-rhel9@sha256:2e9fee8758cfe000f5b304c3de525fc812433fc2ad39122de86140f36c7be04f_amd64 as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhaii/vllm-cuda-rhel9@sha256:5da7a63ad71f6d047a35bfbd572a141be894bae84e60a2b22a237116c477a248_arm64 as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhaii/vllm-cuda-rhel9@sha256:d2ed07d307845135c089bc7644b64734b9349d517abf746c9aa0aa23ed263da5_amd64 as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhaii/vllm-rocm-rhel9@sha256:eb2ca896461f782d8c4c239d36545a1a749d17bebd9fdc0652024092614c69c2_amd64 as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhaii/vllm-spyre-rhel9@sha256:3657354eb0edeb7e0e9aad2a434d7f264626b3d906f4e3e8502a95a73772ca41_s390x as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhaii/vllm-spyre-rhel9@sha256:54ad323a1a44f99991ca9d28cf0a364a44c5bbce143891936f6c668612c3ffb0_amd64 as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhaii/vllm-spyre-rhel9@sha256:b35ecb302c7f4e270f44bf70b7f7f8d053eb74761b1104fea346af9a8e089d09_ppc64le as a component of Red Hat AI Inference Server 3.4; registry.redhat.io/rhelai3/bootc-aws-cuda-rhel9@sha256:a754d4d1126e98f203249414b3831182bb15ee6b3643452f167849defc642e4b_amd64 as a component of Red Hat Enterprise Linux AI 3.4; registry.redhat.io/rhelai3/bootc-azure-cuda-rhel9@sha256:df5b6edd1bdb055219a7385b6d5923f3262c3a408f92da734e3027af55fd593f_amd64 as a component of Red Hat Enterprise Linux AI 3.4; registry.redhat.io/rhelai3/bootc-azure-rocm-rhel9@sha256:8ea1233b1fb6b82d0aa69e9e4c47d2df242001280c11a61584066c27c5bec3a5_amd64 as a component of Red Hat Enterprise Linux AI 3.4; registry.redhat.io/rhelai3/bootc-cuda-rhel9@sha256:a127058368b396a8e8df17dc104469560f40d4451f9135320302568a63380035_arm64 as a component of Red Hat Enterprise Linux AI 3.4; registry.redhat.io/rhelai3/bootc-cuda-rhel9@sha256:b45f3bc25a7d3c9f3bfdc1de3be6db59f6c3109f62326d74fae14e832a797981_amd64 as a component of Red Hat Enterprise Linux AI 3.4; registry.redhat.io/rhelai3/bootc-gcp-cuda-rhel9@sha256:bac5d435d156c3ddcb581d3ff05fdce9f72bd617c5b8435cede16bb17b7bf12e_amd64 as a component of Red Hat Enterprise Linux AI 3.4; registry.redhat.io/rhelai3/bootc-rocm-rhel9@sha256:38ce057f97034bbb8eaea574d41cc7eebaeaa9265a4cdd966476dd3fac129c3c_amd64 as a component of Red Hat Enterprise Linux AI 3.4; registry.redhat.io/rhelai3/disk-image-cuda-rhel9@sha256:5489bd1cdbb7f1a5ce80e9ad688b66c6bb8688b2b202a2a86b5c2205cdd6e126_amd64 as a component of Red Hat Enterprise Linux AI 3.4
Technical terms and abbreviations used in this report
CVE
Common Vulnerabilities and Exposures: the public identifier for one disclosed vulnerability.
CVSS
Common Vulnerability Scoring System: a technical severity framework; it is not patching priority by itself.
EPSS
Exploit Prediction Scoring System: FIRST's estimate of the probability that exploitation activity will be observed in the next 30 days; it is a forecast, not confirmation.
CWE
Common Weakness Enumeration: the standard category describing the underlying software or hardware weakness.
CNA
CVE Numbering Authority: an organisation authorised to assign and publish CVE records.
CISA ADP
Cybersecurity and Infrastructure Security Agency Authorized Data Publisher: structured enrichment added to a CVE record.
NVD
National Vulnerability Database: NIST's enrichment service for CVE records.
CERT / CSIRT
A computer security incident response team that publishes warnings or coordinates incident response.
PoC
Proof of concept: public material that demonstrates or helps reproduce exploitation.
CSAF
Common Security Advisory Framework: a machine-readable format for security advisories.
LoTL
Living off the land: abuse of legitimate tools or system functions during an attack.