# Memory Poisoning Attack and Defense on Memory Based LLM-Agents

arXiv: https://arxiv.org/abs/2601.05504 · HTML: https://mlsanity.com/paper/2601.05504/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 12 of 12)

- [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [Poisoning Language Models During Instruction Tuning](https://mlsanity.com/paper/2305.00944/) (2023)
- [PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models](https://mlsanity.com/paper/2402.07867/) (2024)
- [Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems](https://mlsanity.com/paper/2410.07283/) (2024)
- [A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory](https://mlsanity.com/paper/2510.02373/) (2025)
- [DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents](https://mlsanity.com/paper/2506.12104/) (2025)
- [MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate](https://mlsanity.com/paper/2406.14711/) (2024)
- [How do languages influence each other? Studying cross-lingual data sharing during LM fine-tuning](https://mlsanity.com/paper/2305.13286/) (2023)
- [System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection](https://mlsanity.com/paper/2505.06493/) (2025)
- [A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns](https://mlsanity.com/paper/2410.16155/) (2024)
- [FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systems](https://mlsanity.com/paper/2509.24408/) (2025)

## Built on by (most cited first, 30 of 44)

- [Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats](https://mlsanity.com/paper/2603.11619/) (2026)
- [ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers](https://mlsanity.com/paper/2603.24414/) (2026)
- [Self-Improvements in Modern Agentic Systems: A Survey](https://mlsanity.com/paper/2607.13104/) (2026)
- [Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees](https://mlsanity.com/paper/2606.24322/) (2026)
- [OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences](https://mlsanity.com/paper/2605.18930/) (2026)
- [A Systematic Security Evaluation of OpenClaw and Its Variants](https://mlsanity.com/paper/2604.03131/) (2026)
- [Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory](https://mlsanity.com/paper/2606.25115/) (2026)
- [SoK: Security of Autonomous LLM Agents in Agentic Commerce](https://mlsanity.com/paper/2604.15367/) (2026)
- [Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies](https://mlsanity.com/paper/2606.23075/) (2026)
- [From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents](https://mlsanity.com/paper/2608.10502/) (2026)
- [MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection](https://mlsanity.com/paper/2605.23723/) (2026)
- [Poise: Position-Aware One-Instruction Skill Injection for Silent Execution on LLM Agents](https://mlsanity.com/paper/2606.07943/) (2026)
- [Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation](https://mlsanity.com/paper/2606.10749/) (2026)
- [MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents](https://mlsanity.com/paper/2607.14651/) (2026)
- [When Does Belief-Based Agent Memory Help? Reliability-Conditional Updating and Provenance-Capped Poisoning Defense](https://mlsanity.com/paper/2606.22030/) (2026)
- [Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution](https://mlsanity.com/paper/2603.23064/) (2026)
- [The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory](https://mlsanity.com/paper/2605.09330/) (2026)
- [SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems](https://mlsanity.com/paper/2606.12703/) (2026)
- [Clawed and Dangerous: Can We Trust Open Agentic Systems?](https://mlsanity.com/paper/2603.26221/) (2026)
- [Beyond the Attention Stability Boundary: Agentic Self-Synthesizing Reasoning Protocols](https://mlsanity.com/paper/2604.24512/) (2026)
- [HARP: Measuring Harm Amplification in Multi-Agent LLM Systems](https://mlsanity.com/paper/2605.27489/) (2026)
- [When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents](https://mlsanity.com/paper/2607.05189/) (2026)
- [HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety](https://mlsanity.com/paper/2608.17597/) (2026)
- [SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics](https://mlsanity.com/paper/2604.16358/) (2026)
- [Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation](https://mlsanity.com/paper/2605.06393/) (2026)
- [ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts](https://mlsanity.com/paper/2605.09033/) (2026)
- [Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures](https://mlsanity.com/paper/2605.25435/) (2026)
- [MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents](https://mlsanity.com/paper/2606.10742/) (2026)
- [Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response](https://mlsanity.com/paper/2607.25379/) (2026)
- [S3: Improving Agent Safety through Multi-Stage Defense](https://mlsanity.com/paper/2608.02683/) (2026)

## Abstract (arXiv)

Large language model agents equipped with persistent memory are vulnerable to memory poisoning attacks, where adversaries inject malicious instructions through query only interactions that corrupt the agents long term memory and influence future responses. Recent work demonstrated that the MINJA (Memory Injection Attack) achieves over 95 % injection success rate and 70 % attack success rate under idealized conditions. However, the robustness of these attacks in realistic deployments and effective defensive mechanisms remain understudied. This work addresses these gaps through systematic empirical evaluation of memory poisoning attacks and defenses in Electronic Health Record (EHR) agents. We investigate attack robustness by varying three critical dimensions: initial memory state, number of indication prompts, and retrieval parameters. Our experiments on GPT-4o-mini, Gemini-2.0-Flash and Llama-3.1-8B-Instruct models using MIMIC-III clinical data reveal that realistic conditions with pre-existing legitimate memories dramatically reduce attack effectiveness. We then propose and evaluate two novel defense mechanisms: (1) Input/Output Moderation using composite trust scoring across multiple orthogonal signals, and (2) Memory Sanitization with trust-aware retrieval employing temporal decay and pattern-based filtering. Our defense evaluation reveals that effective memory sanitization requires careful trust threshold calibration to prevent both overly conservative rejection (blocking all entries) and insufficient filtering (missing subtle attacks), establishing important baselines for future adaptive defense mechanisms. These findings provide crucial insights for securing memory-augmented LLM agents in production environments.