memory poisoning

2 items

ARTICLEDEV.to AI·21d ago

Your AI Agent's Memory is a Security Hole — Here's the Fix

The article addresses memory poisoning as a critical, often overlooked security vulnerability in AI agents with persistent memory. This attack involves injecting malicious content into an agent's memory store, causing adversarial behavior in future sessions, a threat distinct from prompt injection.

vulnerability OWASP security memory poisoning

DOCDEV.to AI·5/11/2026

How to Protect Your LangChain Agents from Memory Poisoning (ASI06)

This tutorial addresses memory poisoning in AI agents, a critical vulnerability classified as ASI06 by OWASP. It demonstrates how to protect LangChain agents against this attack using OWASP Agent Memory Guard, an open-source runtime defense layer that screens for prompt injection and credential leakage.

LangChain OWASP learning security