CVE-2025-46722: vllm-project vllm

Vulnerability summary

CVE-2025-46722 is a high (CVSS 7.3) vulnerability in vllm-project vllm. EPSS estimates a 0.32% chance of exploitation in the next 30 days, higher than 23.9% of scored vulnerabilities.

Timeline

1. 29-05-2025
   PublishedVulnerability first disclosed.
2. 29-05-2025
   Last modifiedVulnerability information updated.

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.

• CWE-1023Incomplete Comparison with Missing FactorsThe product performs a comparison between entities that must consider multiple factors or characteristics of each entity, but the comparison does not include one or more of these factors.
• CWE-1288Improper Validation of Consistency within InputThe 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.