vLLM 0.8.0+ OOM DoS via unbounded frame count in VideoMediaIO.load_base64()
CVE-2026-5497 Published on June 11, 2026

Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm
vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication.

NVD

Vulnerability Analysis

CVE-2026-5497 can be exploited with network access, and does not require authorization privileges or user interaction. This vulnerability is considered to have a low attack complexity. An automatable proof of concept (POC) exploit exists. The potential impact of an exploit of this vulnerability is considered to have no impact on confidentiality and integrity, and a high impact on availability.

Attack Vector:
NETWORK
Attack Complexity:
LOW
Privileges Required:
NONE
User Interaction:
NONE
Scope:
UNCHANGED
Confidentiality Impact:
NONE
Integrity Impact:
NONE
Availability Impact:
HIGH

Weakness Types

What is a Resource Exhaustion Vulnerability?

The software does not properly control the allocation and maintenance of a limited resource, thereby enabling an actor to influence the amount of resources consumed, eventually leading to the exhaustion of available resources.

CVE-2026-5497 has been classified to as a Resource Exhaustion vulnerability or weakness.

Allocation of Resources Without Limits or Throttling

The software allocates a reusable resource or group of resources on behalf of an actor without imposing any restrictions on the size or number of resources that can be allocated, in violation of the intended security policy for that actor.


Products Associated with CVE-2026-5497

Want to know whenever a new CVE is published for Red Hat products? stack.watch will email you.

Red Hat Ai Inference Server
 
Red Hat Enterprise Linux Ai
 
Red Hat Openshift Ai
 

Affected Versions

vllm-project/vllm: Red Hat AI Inference Server: Red Hat Enterprise Linux AI (RHEL AI) 3: Red Hat OpenShift AI (RHOAI):

Exploit Probability

EPSS
0.37%
Percentile
28.38%

EPSS (Exploit Prediction Scoring System) scores estimate the probability that a vulnerability will be exploited in the wild within the next 30 days. The percentile shows you how this score compares to all other vulnerabilities.