Incomplete comparison with missing factors in vLLM - CVE-2025-46722

 

Incomplete comparison with missing factors in vLLM - CVE-2025-46722

Published: January 7, 2026


Vulnerability identifier: #VU121084
CSH Severity: Low
CVSS v4: 2.3 [CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:N/VC:L/VI:N/VA:L/SC:N/SI:N/SA:N]
CVE-ID: CVE-2025-46722
CWE-ID: CWE-1023
Exploitation vector: Remote access
Exploit availability: No public exploit available

Vulnerability details

The vulnerability allows a remote user to gain access to sensitive information.

The vulnerability exists due to the MultiModalHasher  class in vllm/multimodal/hasher.py serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the imageâs shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks.


Affected software

vLLM

How to mitigate CVE-2025-46722

Install updates from vendor's website.

vLLM - update to 0.9.0

External References

Related Security Bulletins