Advisory

PYSEC-2025-43

Also known as: CVE-2025-46722, GHSA-c65p-x677-fgj6

Summary

The record has no summary.

Details

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.

Severity

Not rated by the source.

Dates

Published
2025-05-29 17:15 UTC
Modified
2025-05-29 19:42 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0, fixed 0.9.0 (ecosystem)

Fixed versions

0.9.0

Fix

  • Fixed version 0.9.0
    pip install --upgrade vllm==0.9.0

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences