Log in Start free

Vulnerability · Published Jun 11, 2026 · Assigned by @huntr_ai

CVE-2026-5497Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm

High 7.5

In plain English

A high-severity uncontrolled resource consumption in vllm-project/vllm from vllm-project. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 45% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)7.5High
Exploit odds (30 days)0.5%top 54.6% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

Official description

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.

Affected packages & fixed versions

EcosystemPackageFixed inAdvisory
PyPIvllm0.19.0GHSA-wcwg-c5fc-9vrc
PyPIvllm0.19.0PYSEC-2026-2302

Affected products (as reported)

VendorProductVersions
vllm-project vllm-project/vllm unspecified – before 0.19.0

Weakness: CWE-400, CWE-770 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References