CVE Alert: CVE-2025-46722

Vulnerability Summary: 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., 30×100 and 100×30) 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.

Affected Endpoints:

No affected endpoints listed.

Published Date:

5/29/2025, 5:15:21 PM

⚠️ CVSS Score:

Exploit Status:

Not Exploited

References:

• 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

Recommended Action:

No proposed action available. Please refer to vendor documentation for updates.

---