BeClaude
Research2026-05-06

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration

Source: Arxiv CS.AI

arXiv:2605.01970v2 Announce Type: cross Abstract: Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more...

arxivpapersagents