AI agents keep memory across sessions. Conversation history, vector stores, scratchpads, and RAG indexes persist between runs, and anything written into that store becomes a privileged input the agent reads back later. An attacker who plants text in the wrong field can override an agent’s instructions, pull out user data, or steer future tool calls, and the effect survives across sessions because the memory does. Agent Memory Guard is an open-source runtime defense layer that … More →
The post OWASP Agent Memory Guard: Stop AI agents from being weaponized through their own memory appeared first on Help Net Security.