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...

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.

Metrics

CVSS 3.1

7.3/10

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

EPSS Probability

0.27%

18.2th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

Affected Software

Vendor	Product	Versions
Vllm	Vllm	>= 0.7.0, < 0.9.0

References

https://github.com/vllm-project/vllm/commit/99404f53c72965b41558aceb1bc2380875f5d848Patch
https://github.com/vllm-project/vllm/pull/17378Issue Tracking, Patch
https://github.com/vllm-project/vllm/security/advisories/GHSA-c65p-x677-fgj6Vendor Advisory

Timeline

Published: May 29, 2025
Last Modified: Jun 17, 2026
Status: Analyzed

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.

How severe is CVE-2025-46722?

CVE-2025-46722 has a CVSS score of 7.3/10 (HIGH severity). The EPSS model estimates a 0.27% probability of exploitation in the next 30 days.

How do I fix CVE-2025-46722?

Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

How Strix Helps

Related CVEs from 2025

View all 2025CVEs →