1
MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning
通过内存投毒劫持LLM代理的工具选择，一种隐蔽且难检测的新攻击方式。
arXiv:2605.26154v1 Announce Type: cross Abstract: LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attacke…