From Secure Agentic AI to Secure Agentic Web: Challenges, Threats, and Future Directions (opens in new tab)

arXiv:2603.01564v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become real harm through tool use, persistent memory, and interaction with untrusted web content. In this survey, we provide a transition-oriented view from Secure Agentic AI to a Secure Agentic Web. We first summari...