CVE-2025-46722mediumCWE-1023CWE-1288

CVE-2025-46722: medium-severity vulnerability in vllm-project vllm

vLLM has a Weakness in MultiModalHasher Image Hashing Implementation

Published

Follow this CVE+ Monitor vllm+ Monitor vllm

E-mail alert when it lands in KEV, gets a public PoC or its score goes up.

13Vexday Risk Score

No sign of exploitation. No public exploitation artifact known so far.

ssvc Trackcvss 4.2epss 0.3%
In short

vLLM's image hashing system doesn't include image dimensions when creating hashes, so two different-sized images with the same pixels can be mistaken for identical. This causes cache errors and potential data leakage.

Technical detail

The MultiModalHasher in vllm/multimodal/hasher.py uses only PIL.Image.tobytes() for hashing, omitting metadata like width, height, and mode, enabling hash collisions between images of different dimensions. This results in incorrect cache lookups (CWE-1288: Weak Hashing), potentially leading to unauthorized access to cached model outputs or data leakage (CWE-1023: Comparison Using Wrong Factors).

Summary generated and translated by AI from the official 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.
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:N/A:L
Affected products
vllm-project · vllm
Related CVEs — vllm-project vllm

In the same product, most dangerous first.

CVE-2026-22778CRITICALvLLM leaks a heap address when PIL throws an errorEPSS 18.3%CVE-2025-32444CRITICALvLLM Vulnerable to Remote Code Execution via Mooncake IntegrationEPSS 1.8%CVE-2026-27893HIGHvLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-outEPSS 1.4%CVE-2026-48746CRITICALvLLM: OpenAI auth bypassEPSS 1.2%CVE-2026-22807HIGHvLLM affected by RCE via auto_map dynamic module loading during model initializationEPSS 1.0%CVE-2025-47277CRITICALvLLM Allows Remote Code Execution via PyNcclPipe Communication ServiceEPSS 1.0%