Log in Start free

Vulnerability · Published Apr 6, 2026 · Assigned by GitHub_M

CVE-2026-34755vLLM Affected by Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing

Medium 6.5

In plain English

A medium-severity resource allocation without limits in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 42% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)6.5Medium
Exploit odds (30 days)0.5%top 58.2% of all CVEs
Exploited in the wildNo reportsCISA SSVC: none
Attack toolingNoneno public tooling known

Official 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.

Affected packages & fixed versions

EcosystemPackageFixed inAdvisory
PyPIvllm0.19.0GHSA-pq5c-rjhq-qp7p
PyPIvllm0.19.0PYSEC-2026-144

Affected products (as reported)

VendorProductVersions
vllm-project vllm >= 0.7.0, < 0.19.0

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

References