CVE-2026-34755

MEDIUM EPSS 19.4%
Published Apr 6, 20262mo ago · Modified Jun 17, 20261w ago
6.5 CVSS 3.1
Medium
Find Similar
Published Apr 6, 2026 2mo ago
Last Modified Jun 17, 2026 1w ago

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.

CVSS Details

Base Score
6.5
Exploitability
2.8
Impact
3.6
Vector string
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Attack Vector Network
Attack Complexity Low
Privileges Required Low
User Interaction None
Scope Unchanged
Confidentiality None
Integrity None
Availability High

Threat Intelligence

EPSS Exploit Probability
19.4% percentile
Exploit & Patch Status
No Known Exploit
Patch Available

Weaknesses 1

CWE-770

Affected Products 1

VendorProductVersionRange
vllmvllm*≥0.7.0  –  <0.19.0

References 1

  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p
    PatchVendor Advisory

Remediation

  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p
    PatchVendor Advisory