AI agents are increasingly deployed in enterprise environments, inheriting permissions and executing tasks autonomously, often bypassing traditional identity governance controls. This article…
Cybersecurity researchers at Check Point have disclosed three now-patched security flaws in LangGraph, an open-source framework by LangChain for building stateful, multi-agent…
A SQL injection vulnerability in LangGraph's SQLite checkpoint implementation allows attackers to manipulate SQL queries through metadata filter keys, potentially leading to…
An unsafe msgpack deserialization vulnerability in LangGraph that can be exploited to trigger object reconstruction when a checkpoint is loaded by an…
A RediSearch Query Injection vulnerability in @langchain/langgraph-checkpoint-redis that can be used to bypass access controls in self-hosted LangGraph deployments.
LangGraph is a framework that provides standardized primitives for building and orchestrating multi-agent workflows, including tool calling, memory management, and inter-agent communication.