CVE-2026-10800

The CVE-2026-10800 entry concerns PaddlePaddle FastDeploy up to 2.4.1, specifically the MultimodalHasher component’s hasher.py hash_features function. The weakness can allow manipulation that leads to the use of a weak hash, with exploitation requiring local access and carries a high attack compl...

CVE-2026-10800

A weakness has been identified in PaddlePaddle FastDeploy up to 2.4.1. Affected by this issue is the function hashfeatures of the file fastdeploy/multimodal/hasher.py of the component MultimodalHasher. Executing a manipulation can lead to use of weak hash. The attack requires local access. A high...

FastDeploy 安全漏洞

FastDeploy is an open-source tool developed by PaddlePaddle for deploying large language model and visual model inferences. Versions of FastDeploy 2.4.1 and earlier contain security vulnerabilities. These vulnerabilities stem from the weak hashing used in the hashfeatures function of the...

CVE-2026-10800: Use of Weak Hash

A weakness has been identified in PaddlePaddle FastDeploy up to 2.4.1. Affected by this issue is the function hashfeatures of the file fastdeploy/multimodal/hasher.py of the component MultimodalHasher. Executing a manipulation can lead to use of weak hash. The attack requires local access. A high...

The vulnerability of the MultiModalHasher class in the library for working with Large Language Models (LLMs) allows a hacker to disclose protected information.

The vulnerability of the MultiModalHasher class in the library for working with Large Language Models LLMs vLLM is related to improper verification of consistency in input data. Exploiting this vulnerability can allow a remote attacker to disclose sensitive information that is protected by this...

EUVD-2025-16188

Malicious code in bioql PyPI...

CVE-2025-46722 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...

CVE-2025-46722: Improper Validation of Consistency within Input

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...

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...