漏洞信息
尽管我们使用了先进的大模型技术，但其输出仍可能包含不准确或过时的信息。神龙努力确保数据的准确性，但请您根据实际情况进行核实和判断。
Vulnerability Title
Langflow has Authenticated Code Execution in Agentic Assistant Validation
Vulnerability Description
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the implementation reaches dynamic execution sinks and instantiates the generated class server-side. In deployments where an attacker can access the Agentic Assistant feature and influence the model output, this can result in arbitrary server-side Python execution. Version 1.9.0 fixes the issue.
CVSS Information
N/A
Vulnerability Type
对生成代码的控制不恰当(代码注入)
Vulnerability Title
Langflow 代码注入漏洞
Vulnerability Description
Langflow是Langflow开源的一个用于构建多代理和 RAG 应用程序的可视化框架。 Langflow 1.9.0之前版本存在代码注入漏洞，该漏洞源于Agentic Assistant功能在验证阶段执行LLM生成的Python代码，可能导致任意服务器端Python代码执行。
CVSS Information
N/A
Vulnerability Type
N/A