vLLM Affected by Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing

Summary

CVE	CVE-2026-34755
State	PUBLISHED
Assigner	GitHub_M
Source Priority	CVE Program / NVD first with legacy fallback
Published	2026-04-06 16:16:36 UTC
Updated	2026-07-07 12:16:38 UTC
Description	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.

Risk And Classification

Primary CVSS: v3.1 6.5 MEDIUM from ADP

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

EPSS: 0.003780000 probability, percentile 0.297690000 (date 2026-07-08)

Problem Types: CWE-770 | CWE-770 CWE-770: Allocation of Resources Without Limits or Throttling | CWE-770 Allocation of Resources Without Limits or Throttling

Version	Source	Type	Score	Severity	Vector
3.1	ADP	CVSS	6.5	MEDIUM	`CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H`
3.1	[email protected]	Secondary	6.5	MEDIUM	`CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H`
3.1	0b0ca135-0b70-47e7-9f44-1890c2a1c46c	Secondary	6.5	MEDIUM	`CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H`
3.1	CNA	DECLARED	6.5	MEDIUM	`CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H`

CVSS v3.1 Breakdown

Attack Vector

Network

Attack Complexity

Low

Privileges Required

Low

User Interaction

None

Scope

Unchanged

Confidentiality

None

Integrity

None

Availability

High

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

NVD Known Affected Configurations (CPE 2.3)

Type	Vendor	Product	Version	Update	Edition	Language
Application	Vllm	Vllm	All	All	All	All

Vendor Declared Affected Products

Source	Vendor	Product	Version	Platforms
CNA	Vllm-project	Vllm	affected >= 0.7.0, < 0.19.0	Not specified
ADP	Red Hat	Red Hat AI Inference Server 3.2	Not specified	Not specified
ADP	Red Hat	Red Hat AI Inference Server	Not specified	Not specified
ADP	Red Hat	Red Hat Enterprise Linux AI RHEL AI 3	Not specified	Not specified
ADP	Red Hat	Red Hat OpenShift AI RHOAI	Not specified	Not specified

References

Reference	Source	Link	Tags
github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p	[email protected]	github.com	Patch, Vendor Advisory
bugzilla.redhat.com/show_bug.cgi	0b0ca135-0b70-47e7-9f44-1890c2a1c46c	bugzilla.redhat.com
access.redhat.com/security/cve/CVE-2026-34755	0b0ca135-0b70-47e7-9f44-1890c2a1c46c	access.redhat.com
access.redhat.com/errata/RHSA-2026:36006	0b0ca135-0b70-47e7-9f44-1890c2a1c46c	access.redhat.com
security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34755.json	0b0ca135-0b70-47e7-9f44-1890c2a1c46c	security.access.redhat.com
access.redhat.com/errata/RHSA-2026:36005	0b0ca135-0b70-47e7-9f44-1890c2a1c46c	access.redhat.com
CVE Program record	CVE.ORG	www.cve.org	canonical
NVD vulnerability detail	NVD	nvd.nist.gov	canonical, analysis

No vendor comments have been submitted for this CVE.

Additional Advisory Data

Source	Time	Event
ADP	2026-04-06T16:02:21.718Z	Reported to Red Hat.
ADP	2026-04-06T15:38:53.201Z	Made public.

Solutions

ADP: RHSA-2026:36005: Red Hat AI Inference Server 3.2

ADP: RHSA-2026:36006: Red Hat AI Inference Server 3.2

Workarounds

ADP: Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability.

There are currently no legacy QID mappings associated with this CVE.