AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Tian, Xu, Yiwei, Wang, Juan, Guo, Keyan, Xu, Xiaoyang, Xiao, Bowen, Guan, Quanlong, Fan, Jinlin, Liu, Jiawei, Liu, Zhiquan, Hu, Hongxin
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence D.4.6; K.6.5; I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.22724