| Component | vLLM |
| Severity | medium (CVSS 4.2) |
| CVSS vector | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:N/A:L |
| Published (NVD) | 2025-05-29 |
| Last modified | 2026-06-17 |
| Affected versions | vllm >= 0.7.0, < 0.9.0 |
| Fixed in | 0.9.0 |
| Weakness | CWE-1023CWE-1288 |
| CISA KEV | not listed |
NVD 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.
What to do
- Upgrade vLLM to
0.9.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2025-46722
- https://github.com/vllm-project/vllm/security/advisories/GHSA-c65p-x677-fgj6
- https://github.com/vllm-project/vllm/commit/99404f53c72965b41558aceb1bc2380875f5d848
- https://github.com/vllm-project/vllm/pull/17378
Read more
Other vLLM CVEs
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser he...
A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file v...
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/mo...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/r...
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a m...