CVE-2025-46722 — Vllm vulnerability

Vendor	Product	Version range	Fixed in
msrc	azl3_kernel_6.6.47.1-1_on_azure_linux_3.0	—	—
msrc	azl3_kernel_6.6.51.1-5_on_azure_linux_3.0	—	—
msrc	azure_linux_3.0_arm	—	—
msrc	azure_linux_3.0_x64	—	—
msrc	cbl2_kernel_5.15.164.1-1_on_cbl_mariner_2.0	—	—
msrc	cbl2_kernel_5.15.167.1-1_on_cbl_mariner_2.0	—	—
msrc	cbl_mariner_2.0_arm	—	—
msrc	cbl_mariner_2.0_x64	—	—
vllm-project	vllm	—	—
vllm	vllm	>= 0 < 99404f53c72965b41558aceb1bc2380875f5d848	99404f53c72965b41558aceb1bc2380875f5d848
vllm	vllm	>= 0 < 0.9.0	0.9.0
vllm	vllm	>= 0.7.0 < 0.9.0	0.9.0
vllm	vllm	>= 0.7.0 < 0.9.0	0.9.0

Red Hat

vllm: vLLM has a Weakness in MultiModalHasher Image Hashing Implementation

vendor_redhat·2025-05-29·CVSS 4.2

CVE-2025-46722 [MEDIUM] CWE-1023 vllm: vLLM has a Weakness in MultiModalHasher Image Hashing Implementation vllm: vLLM has a Weakness in MultiModalHasher Image Hashing Implementation 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

Microsoft

drm/amdgpu: fix mc_data out-of-bounds read warning

vendor_msrc·2024-09-10·CVSS 7.1

CVE-2024-46722 [HIGH] CWE-125 drm/amdgpu: fix mc_data out-of-bounds read warning drm/amdgpu: fix mc_data out-of-bounds read warning FAQ: Is Azure Linux the only Microsoft product that includes this open-source library and is therefore potentially affected by this vulnerability? One of the main benefits to our customers who choose to use the Azure Linux distro is the commitment to keep it up to date with the most recent and most secure versions of the open source libraries with which the distro is composed. Microsoft is committed to transparency in this work which is why we began publishing CSAF/VEX in October 2025. See this blog post for more information. If impact to additional products is identified, we will update the CVE to reflect this. Mariner: Mariner Linux: Linux Customer Action Required: Yes Remediation: CBL-Mariner Releases Reference: https://learn.micr

OSV

CVE-2025-46722: vLLM is an inference and serving engine for large language models (LLMs)

osv·2025-05-29

CVE-2025-46722 CVE-2025-46722: vLLM is an inference and serving engine for large language models (LLMs) 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.

OSV

vLLM has a Weakness in MultiModalHasher Image Hashing Implementation

osv·2025-05-28

CVE-2025-46722 [MEDIUM] vLLM has a Weakness in MultiModalHasher Image Hashing Implementation vLLM has a Weakness in MultiModalHasher Image Hashing Implementation ## Summary 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. ## Details - **Affected file:** `vllm/multimodal/hasher.py` - **Affected method:** `MultiModalHasher.serialize_item` https://github.com/vllm-projec

GHSA

vLLM has a Weakness in MultiModalHasher Image Hashing Implementation

ghsa·2025-05-28

CVE-2025-46722 [MEDIUM] CWE-1023 vLLM has a Weakness in MultiModalHasher Image Hashing Implementation vLLM has a Weakness in MultiModalHasher Image Hashing Implementation ## Summary 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. ## Details - **Affected file:** `vllm/multimodal/hasher.py` - **Affected method:** `MultiModalHasher.serialize_item` https://github.com/vllm-projec

CVE-2025-46722: 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…

Affected

CVSS provenance