cs.AINov 1, 2026

MemHarmBench: Evaluating Cross-Session Prompt Injection in Memory-Persistent AI Agents

Authors: Zhihua Wang, Yunhao Feng, Yifeng Gao, Rui Pan, Baiheng Zhao, Zixing Chen, Xingjun Ma

Organizations: Fudan University · University of Shanghai for Science and Technology · Alibaba Group · Shanghai Innovation Institute

Abstract

AI agents often rely on persistent memory to retain user preferences and operational rules across sessions. However, this capability introduces a new safety risk: malicious instructions from messages, documents, or Web content can be retained in memory and influence future tasks even after the original attack content is removed. Existing attack success metrics, however, fail to capture who is affected and how attacks translate into downstream harm during otherwise normal task execution. We introduce MemHarmBench, a victim-centric benchmark for evaluating cross-session prompt injection in memory-persistent AI agents. MemHarmBench considers three categories of potential victims: users, workspace/project owners, and external stakeholders. Our evaluation first exposes an agent to malicious instructions and tests whether they are retained in memory. We then remove the attack content and initiate a new session with a legitimate task while preserving the agent's memory. We jointly evaluate whether the agent follows the attacker's intent, completes the legitimate task, and exhibits observable execution anomalies. Across multiple agent systems, we find that cross-session attacks can remain behaviorally stealthy: agents often complete tasks normally and exhibit no detectable anomalies while still making critical decisions aligned with the attacker's intent. By connecting malicious memory retention to downstream decisions and affected parties, MemHarmBench provides a systematic framework for exposing safety risks that conventional attack- and task-success metrics may overlook. We publicly release MemHarmBench at https://github.com/Kirito14IT/MemHarmBench.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jul 16, 2026

Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems

A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases. While this makes agents more useful and self-improving, it also creates a new attack surface for prompt injections in which malicious instructions can be embedded within persistent files and influence future behavior. In this work, we study prompt injection attacks in memory-based agentic systems using a sandboxed synthetic workspace. We evaluate two agentic systems, Anthropic Claude Code and OpenAI Codex, across four models: Claude Haiku 4.5, Claude Opus 4.7, GPT-5.2, and GPT-5.5. Our results show that although it is difficult to make an agent overwrite its own memory files using untrusted external content, payloads already planted in those files can successfully attack current and future sessions. Attack success and payload persistence vary substantially across systems, models, adversarial goals, and multi-session attack sequences. These findings show that persistent memory changes the threat model for prompt injection and motivate defenses that protect memory updates without removing useful agent adaptation.
Jun 3, 2026

What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in Agentic Systems

Modern agentic systems transform LLMs from session-bounded assistants into stateful systems that persist and evolve shared world state across sessions through memories, filesystems, tools, and other long-lived contextual artifacts. This shift fundamentally expands the attack surface of prompt injection. However, prior works on prompt injection have largely focused on model-level threats within a single session, overlooking how cross-session persistent system state fundamentally changes the system-level risk of agentic systems. Inspired by stored cross-site scripting in web systems, we introduce cross-session stored prompt injection, where a successful injection can persist within agentic system state and silently influence future executions long after the original attacker interaction has ended. To systematically study this threat, we formalize stored prompt injection and develop a taxonomy of how adversarial content persists and affects agentic systems across sessions. We further develop a benchmark and sandbox toolkit to evaluate the risks of stored prompt injection, enabling quantitative analysis of attack success across different models, attack goals, and persistence channels. Our findings highlight that persistence transforms prompt injection from an ephemeral model-level threat into a long-lived system-level vulnerability embedded within agent execution state. We hope this work draws broader attention to this emerging threat and motivates the community to systematically study and mitigate system risks arising from persistence in agentic systems.
Sep 12, 2026

When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based Agents

Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also introduces security and privacy risks because malicious instructions from external sources may be written into persistent memory and persist across sessions. To study this risk, we propose PMPA, a Persistent Memory Poisoning Attack against harness-based agents. PMPA embeds malicious instructions into benign external sources and induces the victim agent to write them into persistent memory without directly accessing to the agent framework. Once stored, the poisoned memory can be retrieved in later sessions, triggering additional malicious actions and causing privacy leakage. We evaluate PMPA on OpenClaw and Claude Code across different backbone LLMs, input modalities, and trigger scenarios. Across all settings, PMPA achieves average Injection Success Rate (ISR) and Cross-session Attack Success Rate (C-ASR) of 73.7%/ 55.5% on OpenClaw and 66.9%/ 81.7% on Claude Code, while preserving benign task performance on both systems. We further evaluate a targeted prompt-level defense and find that it can reduce memory injection in many settings, but provides limited protection once the persistent memory has been poisoned.