780 matches found
vLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypoints
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer RPC server entrypoints. The core functionality runserverloop calls the function makehandlercoro, which directly uses cloudpickle.loads on received messages without any sanitization. This can result in remote code...
Deserialization of Untrusted Data
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Deserialization of Untrusted Data in the makehandlercoro function used by the async RPC server for communication between nodes, which uses pickle fo...
GHSA-PGR7-MHP5-FGJP vLLM deserialization vulnerability in vllm.distributed.GroupCoordinator.recv_object
vllm-project vllm version 0.6.0 contains a vulnerability in the distributed training API. The function vllm.distributed.GroupCoordinator.recvobject deserializes received object bytes using pickle.loads without sanitization, leading to a remote code execution vulnerability. Maintainer perspective...
GHSA-CJ47-QJ6G-X7R4 vLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypoints
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer RPC server entrypoints. The core functionality runserverloop calls the function makehandlercoro, which directly uses cloudpickle.loads on received messages without any sanitization. This can result in remote code...
GHSA-XQGJ-R6XV-9CW4 Withdrawn Advisory: Dask Vulnerable to Command Injection
Withdrawn Advisory This advisory has been withdrawn because it describes intended functionality. This link is maintained to preserve external references. Original Description Dask versions =2024.8.2 contain a vulnerability in the Dask Distributed Server where the use of pickle serialization allow...
PYSEC-2025-222
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer RPC server entrypoints. The core functionality runserverloop calls the function makehandlercoro, which directly uses cloudpickle.loads on received messages without any sanitization. This can result in remote code...
CVE-2024-12433
A vulnerability in infiniflow/ragflow versions v0.12.0 allows for remote code execution. The RPC server in RagFlow uses a hard-coded AuthKey 'authkey=b'infiniflow-token4kevinhu'' which can be easily fetched by attackers to join the group communication without restrictions. Additionally, the serve...
CVE-2024-12433
A vulnerability in infiniflow/ragflow versions v0.12.0 allows for remote code execution. The RPC server in RagFlow uses a hard-coded AuthKey 'authkey=b'infiniflow-token4kevinhu'' which can be easily fetched by attackers to join the group communication without restrictions. Additionally, the serve...
CVE-2024-12433
CVE-2024-12433 affects infiniflow/ragflow v0.12.0. The RPC server uses a hard-coded AuthKey (authkey=b'infiniflow-token4kevinhu') and deserializes incoming data with pickle.loads() on connection.recv(), enabling remote code execution. Fixed in v0.14.0. A PoC/proof-of-concept is available in publi...
CVE-2024-12433 Remote Code Execution in infiniflow/ragflow
A vulnerability in infiniflow/ragflow versions v0.12.0 allows for remote code execution. The RPC server in RagFlow uses a hard-coded AuthKey 'authkey=b'infiniflow-token4kevinhu'' which can be easily fetched by attackers to join the group communication without restrictions. Additionally, the serve...
CVE-2024-12044 Remote Code Execution by Pickle Deserialization in open-mmlab/mmdetection
A remote code execution vulnerability exists in open-mmlab/mmdetection version v3.3.0. The vulnerability is due to the use of the pickle.loads function in the allreducedict distributed training API without proper sanitization. This allows an attacker to execute arbitrary code by broadcasting a...
CVE-2024-12044 Remote Code Execution by Pickle Deserialization in open-mmlab/mmdetection
A remote code execution vulnerability exists in open-mmlab/mmdetection version v3.3.0. The vulnerability is due to the use of the pickle.loads function in the allreducedict distributed training API without proper sanitization. This allows an attacker to execute arbitrary code by broadcasting a...
CVE-2024-11039
A pickle deserialization vulnerability exists in the Latex English error correction plug-in function of binary-husky/gptacademic versions up to and including 3.83. This vulnerability allows attackers to achieve remote command execution by deserializing untrusted data. The issue arises from the...
PT-2025-12261
Name of the Vulnerable Software and Affected Versions vllm-project vllm version 0.6.0 Description The issue concerns a remote code execution vulnerability in the distributed training API. Specifically, the vllm.distributed.GroupCoordinator.recv object function deserializes received object bytes...
CVE-2024-12433: Deserialization of Untrusted Data
A vulnerability in infiniflow/ragflow versions v0.12.0 allows for remote code execution. The RPC server in RagFlow uses a hard-coded AuthKey 'authkey=b'infiniflow-token4kevinhu'' which can be easily fetched by attackers to join the group communication without restrictions. Additionally, the serve...
RAGFlow 代码问题漏洞
RAGFlow is an open source RAG engine based on deep document understanding from InfiniFlow Open Source. A code issue vulnerability exists in RAGFlow version v0.12.0, which stems from hard-coded AuthKey and pickle deserialization and could lead to remote code execution...
dmlc/dgl Vulnerable to Remote Code Execution by Pickle Deserialization via rpc.recv_request()
Impact Dgl implements rpc server startserver in rpcserver.py for supporting the RPC communications among different remote users over networks. It relies on pickle serialize and deserialize to pack and unpack network messages. The is a known risk in pickle deserialization functionality that can be...