1
Beyond Direct Access: Resource Hijacking in LLM Agents
揭露LLM智能体新型攻击面：资源劫持如何绕过直接权限，威胁比你想象的更隐蔽。
arXiv:2608.15108v1 Announce Type: cross Abstract: Large language model agents are increasingly connected to high-value resources such as computing inf…