CVE-2025-6279

CVE-2025-6279 affects Upsonic up to 0.55.6. The vulnerability resides in the Pickle Handler’s function cloudpickle.loads (file /tools/add_tool) and enables deserialization due to the underlying root cause described in the coordinated disclosure. Exploit information is publicly disclosed according...

Upsonic 代码问题漏洞

Upsonic is an AI agent framework open-sourced by Upsonic. A code issue vulnerability exists in Upsonic 0.55.6 and earlier versions, which stems from deserialization of the file /tools/addtool function cloudpickle.loads in the component Pickle Handler...

Arbitrary Code Execution

InspireMusic is vulnerable to Arbitrary Code Execution. The vulnerability is due to insecure deserialization due to unsafe use of Python's pickle module in the loadstatedict function, which can allow attackers to execute arbitrary code when loading untrusted data...

pypickle 安全漏洞

pypickle is a tool by Erdogan Personal Developers for saving and loading files in pickle format. A security vulnerability exists in pypickle version 1.1.5 and earlier, which stems from improper authorization...

CVE-2024-35059

An issue in the Pickle Python library of NASA AIT-Core v2.5.2 allows attackers to execute arbitrary commands...

CVE-2023-23930

vantage6 is privacy preserving federated learning infrastructure. Versions prior to 4.0.0 use pickle, which has known security issue, as a default serialization module but that has known security issues. All users of vantage6 that post tasks with the default serialization are affected. Version...

CVE-2023-32321

CKAN is an open-source data management system for powering data hubs and data portals. Multiple vulnerabilities have been discovered in Ckan which may lead to remote code execution. An arbitrary file write in resourcecreate and packageupdate actions, using the ResourceUploader object. Also...

GHSA-HJQ4-87XH-G4FV vLLM Allows Remote Code Execution via PyNcclPipe Communication Service

Impacted Environments This issue ONLY impacts environments using the PyNcclPipe KV cache transfer integration with the V0 engine. No other configurations are affected. Summary vLLM supports the use of the PyNcclPipe class to establish a peer-to-peer communication domain for data transmission...

Remote Code Execution (RCE)

vllm is vulnerable to Remote Code Execution RCE. The vulnerability is due to the use of Python’s pickle module on untrusted data received over a ZeroMQ SUB socket in multi-node deployments using the V0 engine, which allows an attacker to execute arbitrary code on the target machine and potentiall...

CVE-2025-30165 Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration

vLLM is an inference and serving engine for large language models. In a multi-node vLLM deployment using the V0 engine, vLLM uses ZeroMQ for some multi-node communication purposes. The secondary vLLM hosts open a SUB ZeroMQ socket and connect to an XPUB socket on the primary vLLM host. When data ...

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 via the SUB ZeroMQ socket, where the deserialization is performed using the unsafe pickle library. An attacker on...

Deserialization of Untrusted Data

Overview rtc-tools is a Toolbox for control and optimization of water systems. Affected versions of this package are vulnerable to Deserialization of Untrusted Data rough cashing in pickle module in csvlookuptablemixin.py. An attacker could potentially execute arbitrary code by exploiting the...

PYSEC-2025-42

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerab...

CVE-2025-32444

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerab...

PYSEC-2025-42

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerab...

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 Mooncake integration. An attacker can execute arbitrary code by sending malicious payloads to a pickle base...

vLLM 代码问题漏洞

vLLM is a vLLM open source high throughput and memory efficient inference and service engine for LLM. A code issue vulnerability exists in vLLM versions prior to 0.6.5 to 0.8.5, which stems from the use of pickle-based serialization and could lead to remote code execution...

GHSA-HJ4W-HM2G-P6W5 vLLM Vulnerable to Remote Code Execution via Mooncake Integration

Impacted Deployments Note that vLLM instances that do NOT make use of the mooncake integration are NOT vulnerable. Description vLLM integration with mooncake is vaulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were...

GHSA-7V4R-C989-XH26 BentoML's runner server Vulnerable to Remote Code Execution (RCE) via Insecure Deserialization

Summary There was an insecure deserialization in BentoML's runner server. By setting specific headers and parameters in the POST request, it is possible to execute any unauthorized arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure o...

Picklescan missing detection when calling built-in python library function timeit.timeit()

Summary Using timeit.timeit function, which is a built-in python library function to execute remote pickle file. Details Pickle’s deserialization process is known to allow execution of function via reduce method. While Picklescan is meant to detect such exploits, this attack evades detection by...