Know every vulnerabilitybefore it knows you.
DevGuard continuously monitors your dependencies and alerts you when CVEs like this one affect your stack — with real-time threat intelligence built for developers.
PYSEC-2025-43
No affected components available
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.
Measures severity based on intrinsic characteristics of the vulnerability, independent of environment.
No exploitation activity has been observed at this time. Continue routine monitoring.
The exploit probability is very low. The vulnerability is unlikely to be exploited in the next 30 days.
We did not find any exploit available. Neither in GitHub repositories nor in the Exploit-Database.
Continuously monitor your dependencies and get alerted when vulnerabilities like this one affect your stack.
Checkout DevGuard