SecuriTricks - CVE-2026-34755

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.

Product(s) Impacted

Vendor	Product	Versions
Vllm	Vllm	0.7.0-0.19.0

Weaknesses

Common security weaknesses mapped to this vulnerability.

CWE-770

Allocation of Resources Without Limits or Throttling

The product 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.

*CPE(s)

Affected systems and software identified for this CVE.

Type	Vendor	Product	Version	Update	Edition	Language	Software Edition	Target Software	Target Hardware	Other Information
a	vllm	vllm	0.7.0-0.19.0	/	/	/	/	/	/	/

References

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

CVSS Score

6.5 / 10

CVSS Data - 3.1

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

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

View Vector String

Timeline

Published: April 6, 2026, 4:16 p.m.
Last Modified: April 7, 2026, 1:20 p.m.

Status : Undergoing Analysis

CVE has been recently published to the CVE List and has been received by the NVD.

More info

Source

[email protected]

CVE-2026-34755