https://cve.radiocsirt.org Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Sat, 03 Oct 2026 03:05:13 +0000 https://cve.radiocsirt.org/vuln/cve-2025-46722 <p><strong>Affected:</strong> vllm-project vllm</p> <p>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.</p> <p><strong>Affected:</strong> vllm-project vllm</p> <p>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.</p> https://cve.radiocsirt.org/vuln/cve-2025-46722 https://cve.radiocsirt.org/vuln/ghsa-c65p-x677-fgj6 <p><strong>Affected:</strong> PyPI: vllm</p> <p>## Summary</p> <p>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.</p> <p>## Details</p> <p>- **Affected file:** `vllm/multimodal/hasher.py` - **Affected method:** `MultiModalHasher.serialize_item` https://github.com/vllm-project/vllm/blob/9420a1fc30af1a632bbc2c66eb8668f3af41f026/vllm/multimodal/hasher.py#L34-L35 - **Current behavior:** For `Image.Image` instances, only `obj.tobytes()` is used for hashing. - **Problem description:** `obj.tobytes()` does not include the image’s width, height, or mode metadata. - **Impact:** Two images with the same pixel byte sequence but different sizes could be regarded as the same image by the cache and hashing system, which may result in: - Incorrect cache hits, leading to abnormal responses - Deliberate construction of images with different meanings but the same hash value</p> <p>## Recommendation</p> <p>In the `serialize_item` method, **serialization of `Image.Image` objects should include not only pixel data, but also all critical metadata**—such…</p> <p><strong>Affected:</strong> PyPI: vllm</p> <p>## Summary</p> <p>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.</p> <p>## Details</p> <p>- **Affected file:** `vllm/multimodal/hasher.py` - **Affected method:** `MultiModalHasher.serialize_item` https://github.com/vllm-project/vllm/blob/9420a1fc30af1a632bbc2c66eb8668f3af41f026/vllm/multimodal/hasher.py#L34-L35 - **Current behavior:** For `Image.Image` instances, only `obj.tobytes()` is used for hashing. - **Problem description:** `obj.tobytes()` does not include the image’s width, height, or mode metadata. - **Impact:** Two images with the same pixel byte sequence but different sizes could be regarded as the same image by the cache and hashing system, which may result in: - Incorrect cache hits, leading to abnormal responses - Deliberate construction of images with different meanings but the same hash value</p> <p>## Recommendation</p> <p>In the `serialize_item` method, **serialization of `Image.Image` objects should include not only pixel data, but also all critical metadata**—such…</p> https://cve.radiocsirt.org/vuln/ghsa-c65p-x677-fgj6