vLLM up to 0.8.x hasher.py MultiModalHasher improper validation of consistency within input

Summaryinfo

A vulnerability was found in vLLM up to 0.8.x. It has been declared as problematic. This affects the function MultiModalHasher of the file vllm/multimodal/hasher.py. The manipulation results in improper validation of consistency within input. This vulnerability is cataloged as CVE-2025-46722. The attack may be launched remotely. There is no exploit available. It is recommended to upgrade the affected component.

Detailsinfo

A vulnerability classified as problematic has been found in vLLM up to 0.8.x. Affected is the function MultiModalHasher of the file vllm/multimodal/hasher.py. The manipulation with an unknown input leads to a improper validation of consistency within input vulnerability. CWE is classifying the issue as CWE-1288. The product receives a complex input with multiple elements or fields that must be consistent with each other, but it does not validate or incorrectly validates that the input is actually consistent. This is going to have an impact on confidentiality, and availability. CVE summarizes:

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.

The advisory is available at github.com. This vulnerability is traded as CVE-2025-46722 since 04/28/2025. The exploitability is told to be difficult. It is possible to launch the attack remotely. Technical details are known, but there is no available exploit.

Upgrading to version 0.9.0 eliminates this vulnerability. Applying the patch 99404f53c72965b41558aceb1bc2380875f5d848 is able to eliminate this problem. The bugfix is ready for download at github.com. The best possible mitigation is suggested to be upgrading to the latest version.

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Productinfo

Name

• vLLM

Version

• 0.1
• 0.2
• 0.3
• 0.4
• 0.5
• 0.6
• 0.7
• 0.8

License

• open-source

CPE 2.3info

• 🔍
• 🔍
• 🔍

CPE 2.2info

• 🔍
• 🔍
• 🔍

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Discussion