When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Xiaoyu, Du, Minxin, Xie, Qipeng, Ke, Haobin, Ye, Qingqing, Hu, Haibo
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913099345297408
author Xu, Xiaoyu
Du, Minxin
Xie, Qipeng
Ke, Haobin
Ye, Qingqing
Hu, Haibo
author_facet Xu, Xiaoyu
Du, Minxin
Xie, Qipeng
Ke, Haobin
Ye, Qingqing
Hu, Haibo
contents Personalized LLM agents maintain persistent cross-session state to support long-horizon collaboration. Yet, this persistence introduces a subtle but critical security vulnerability: routine user-agent interactions can gradually reshape an agent's long-term state, inadvertently weakening future confirmation boundaries, expanding tool-use defaults, and escalating autonomous behavior over time. We formalize this risk as \textbf{unintended long-term state poisoning}. To systematically study it, we introduce the \textbf{Unintended Long-Term State Poisoning Bench (ULSPB)}, a bilingual benchmark comprising $350$ settings spanning five assistance categories, seven interaction patterns, 24-turn routine interactions, and matched single-injection counterparts. Furthermore, we define the \emph{Harm Score} (HS), a state-centric metric that quantifies \emph{authorization drift}, \emph{tool-use escalation}, and \emph{unchecked autonomy}. Experiments on OpenClaw with four backbone LLMs demonstrate that, while single-injection is generally effective, routine conversations alone can substantially poison long-term state, primarily corrupting memory-centric artifacts. Evaluations seeded with real-world user interactions confirm that this risk is not a mere artifact of synthetic prompts. To mitigate this threat, we propose \textbf{StateGuard}, a lightweight, post-execution defense that audits state diffs at the writeback boundary and selectively rolls back dangerous edits. Across all evaluated models, StateGuard reduces HS to near zero and lowers false-negative rates, with acceptable high false-positive rates under a safety-first writeback defense and minimal overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06731
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents
Xu, Xiaoyu
Du, Minxin
Xie, Qipeng
Ke, Haobin
Ye, Qingqing
Hu, Haibo
Cryptography and Security
Computation and Language
Machine Learning
Personalized LLM agents maintain persistent cross-session state to support long-horizon collaboration. Yet, this persistence introduces a subtle but critical security vulnerability: routine user-agent interactions can gradually reshape an agent's long-term state, inadvertently weakening future confirmation boundaries, expanding tool-use defaults, and escalating autonomous behavior over time. We formalize this risk as \textbf{unintended long-term state poisoning}. To systematically study it, we introduce the \textbf{Unintended Long-Term State Poisoning Bench (ULSPB)}, a bilingual benchmark comprising $350$ settings spanning five assistance categories, seven interaction patterns, 24-turn routine interactions, and matched single-injection counterparts. Furthermore, we define the \emph{Harm Score} (HS), a state-centric metric that quantifies \emph{authorization drift}, \emph{tool-use escalation}, and \emph{unchecked autonomy}. Experiments on OpenClaw with four backbone LLMs demonstrate that, while single-injection is generally effective, routine conversations alone can substantially poison long-term state, primarily corrupting memory-centric artifacts. Evaluations seeded with real-world user interactions confirm that this risk is not a mere artifact of synthetic prompts. To mitigate this threat, we propose \textbf{StateGuard}, a lightweight, post-execution defense that audits state diffs at the writeback boundary and selectively rolls back dangerous edits. Across all evaluated models, StateGuard reduces HS to near zero and lowers false-negative rates, with acceptable high false-positive rates under a safety-first writeback defense and minimal overhead.
title When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents
topic Cryptography and Security
Computation and Language
Machine Learning
url https://arxiv.org/abs/2605.06731