CVE-2025-46722

Description

vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image’s 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. This issue has been patched in version 0.9.0.

CVSS v3.1 Score

4.2

MEDIUM

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

Weakness Type (CWE)

CWE-1023 CWE-1023

CWE-1288 CWE-1288

Affected Products

Vendor	Product	Versions
vllm	vllm	0.7.0 — 0.9.0

References

Advisories & Patches

https://github.com/vllm-project/vllm/commit/99404f53c72965b41558aceb1bc2380875f5d848 https://github.com/vllm-project/vllm/pull/17378 https://github.com/vllm-project/vllm/security/advisories/GHSA-c65p-x677-fgj6

Frequently Asked Questions

What is CVE-2025-46722? +

vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image’s 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. This issue has been patched in version 0.9.0. It has a CVSS v3.1 base score of 4.2 (MEDIUM).

How severe is CVE-2025-46722? +

CVE-2025-46722 has a CVSS v3.1 score of 4.2 out of 10, rated MEDIUM. This is a medium-severity vulnerability that should be remediated as part of regular maintenance.

What products are affected by CVE-2025-46722? +

CVE-2025-46722 affects products from vllm, specifically: vllm. Check the affected products table above for specific version ranges.

How do I check if I'm vulnerable to CVE-2025-46722? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2025-62000 7.1

BullWall Ransomware Containment may not always detect an encrypted file. This issue affects a specific file inspection method that evaluates …

CVE-2026-53839 6.5

OpenClaw before 2026.5.7 contains a hostname validation vulnerability in retry endpoint checks that allows matching hostname prefixes instead of exact …

CVE-2026-53859 6.5

OpenClaw before 2026.5.26 contains a hostname validation vulnerability allowing attackers to bypass blocklist comparisons using trailing-dot notation in model or …

CVE-2025-55333 6.1

Incomplete comparison with missing factors in Windows BitLocker allows an unauthorized attacker to bypass a security feature with a physical …

CVE-2026-7473 5.8

On affected platforms running Arista EOS where a tunnel decapsulation configuration—such as VXLAN (Virtual Extensible LAN), decap-groups, or a GRE …

CVE-2024-5528 3.5

An issue was discovered in GitLab CE/EE affecting all versions prior to 16.11.6, starting from 17.0 prior to 17.0.4, and …