Vulnerability in Vllm
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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 4.2 (Medium). Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:N/A:L.
EPSS exploit prediction
EPSS: 0.003 (23.9th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 24th percentile — 23.9% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.003 · newest: 0.003 · change: +0.000
Affected products
- Vllm
- Vllm-Project Vllm — versions >= 0.7.0, < 0.9.0
Weakness classification (CWE)
References
- github.com/vllm-project/vllm/security/advisories/GHSA-c65p-x677-fgj6 (Vendor Advisory)
- github.com/vllm-project/vllm/pull/17378 (Patch, Issue Tracking)
- github.com/vllm-project/vllm/commit/99404f53c72965b41558aceb1bc2380875f5d848 (Patch)
Frequently asked questions
- What is CVE-2025-46722?
- CVE-2025-46722 is a medium-severity vulnerability in Vllm, classified under CWE-1023. CVSS score: 4.2/10. Published 2025-05-29.
- How severe is CVE-2025-46722?
- Medium severity. CVSS v3 base score is 4.2 out of 10.