AI RESEARCH
SafeAgent: A Runtime Protection Architecture for Agentic Systems
arXiv CS.AI
•
ArXi:2604.17562v1 Announce Type: new Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection. This paper presents SafeAgent, a runtime security architecture that treats agent safety as a stateful decision problem over evolving interaction trajectories.