Jul 2026
MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents
This work proposes MemPoison, a comprehensive benchmark and analysis framework featuring 1227 hand-validated cases across four attack types, three injection channels, and three representative memory substrates, evaluated on seven open-weight and three closed-weight model families.
Ji-Feng Gao, Kang Xia, Yi Zhang et al.
· arXiv.org · 3 citations