Incomplete Comparison with Missing Factors The advisory has been revoked - it doesn't affect any version of package py3.10-vllm-cuda-12.6  (opens in a new tab)

The Chainguard security team deemed this advisory irrelevant for Chainguard:latest.

Note: Versions mentioned in the description apply only to the upstream py3.10-vllm-cuda-12.6 package and not the py3.10-vllm-cuda-12.6 package as distributed by Chainguard.

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.

• https://github.com/vllm-project/vllm/commit/99404f53c72965b41558aceb1bc2380875f5d848
• https://github.com/vllm-project/vllm/pull/17378
• https://github.com/vllm-project/vllm/security/advisories/GHSA-c65p-x677-fgj6