CVE-2025-46722
May 30, 2025, 4:31 p.m.
4.2
Medium
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.
Product(s) Impacted
| Vendor | Product | Versions |
|---|---|---|
| Vllm |
|
|
Weaknesses
Common security weaknesses mapped to this vulnerability.
CWE-1023
Incomplete Comparison with Missing Factors
The 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.
*CPE(s)
Affected systems and software identified for this CVE.
| Type | Vendor | Product | Version | Update | Edition | Language | Software Edition | Target Software | Target Hardware | Other Information |
|---|---|---|---|---|---|---|---|---|---|---|
| a | vllm | vllm | 0.7.0-0.9.0 | / | / | / | / | / | / | / |
Tags
CVSS Score
CVSS Data - 3.1
- Attack Vector: NETWORK
- Attack Complexity: HIGH
- Privileges Required: LOW
- Scope: UNCHANGED
- Confidentiality Impact: LOW
- Integrity Impact: NONE
- Availability Impact: LOW
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:N/A:L
Timeline
Published: May 29, 2025, 5:15 p.m.
Last Modified: May 30, 2025, 4:31 p.m.
Last Modified: May 30, 2025, 4:31 p.m.
Status : Awaiting Analysis
CVE has been recently published to the CVE List and has been received by the NVD.
More infoSource
security-advisories@github.com
*Disclaimer: Some vulnerabilities do not have an associated CPE. To enhance the data, we use AI to infer CPEs based on CVE details. This is an automated process and might not always be accurate.