Minja sneak attack poisons AI models for other chatbot users

preprint paper: “A Practical Memory Injection Attack against LLM Agents“<p>* <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2503.03704" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2503.03704</a>