# Multi-Agent Systems Execute Arbitrary Malicious Code

arXiv: https://arxiv.org/abs/2503.12188 · HTML: https://mlsanity.com/paper/2503.12188/

## Key facts

- Cited by 53 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 41 of its 82 references that are in the map.
- First posted on arXiv 15 Mar 2025.

## 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, 30 of 41)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [StruQ: Defending Against Prompt Injection with Structured Queries](https://mlsanity.com/paper/2402.06363/) (2024)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [Defending Against Indirect Prompt Injection Attacks With Spotlighting](https://mlsanity.com/paper/2403.14720/) (2024)
- [Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks](https://mlsanity.com/paper/2411.04468/) (2024)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [SecAlign: Defending Against Prompt Injection with Preference Optimization](https://mlsanity.com/paper/2410.05451/) (2024)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems](https://mlsanity.com/paper/2410.07283/) (2024)
- [The Ethics of Advanced AI Assistants](https://mlsanity.com/paper/2404.16244/) (2024)
- [Jatmo: Prompt Injection Defense by Task-Specific Finetuning](https://mlsanity.com/paper/2312.17673/) (2023)
- [On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents](https://mlsanity.com/paper/2408.00989/) (2024)
- [The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents](https://mlsanity.com/paper/2412.16682/) (2024)
- [System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective](https://mlsanity.com/paper/2409.19091/) (2024)
- [Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities](https://mlsanity.com/paper/2407.07791/) (2024)

## Built on by (most cited first, 30 of 53)

- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [SAGA: A Security Architecture for Governing AI Agentic Systems](https://mlsanity.com/paper/2504.21034/) (2025)
- [Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI](https://mlsanity.com/paper/2505.19443/) (2025)
- [A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents](https://mlsanity.com/paper/2506.23844/) (2025)
- [AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities](https://mlsanity.com/paper/2508.11126/) (2025)
- [SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems](https://mlsanity.com/paper/2505.24201/) (2025)
- [SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration](https://mlsanity.com/paper/2603.21019/) (2026)
- [Securing GenAI Multi-Agent Systems Against Tool Squatting: A Zero Trust Registry-Based Approach](https://mlsanity.com/paper/2504.19951/) (2025)
- [Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems](https://mlsanity.com/paper/2601.07072/) (2026)
- [BlockA2A: Towards Secure and Verifiable Agent-to-Agent Interoperability](https://mlsanity.com/paper/2508.01332/) (2025)
- [From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration](https://mlsanity.com/paper/2603.04474/) (2026)
- [ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection](https://mlsanity.com/paper/2605.03378/) (2026)
- [Breaking and Fixing Defenses Against Control-Flow Hijacking in Multi-Agent Systems](https://mlsanity.com/paper/2510.17276/) (2025)
- [Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs](https://mlsanity.com/paper/2512.04668/) (2025)
- [Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies](https://mlsanity.com/paper/2510.14312/) (2025)
- [OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage](https://mlsanity.com/paper/2602.13477/) (2026)
- [STAC: When Innocent Tools Form Dangerous Chains for LLM Agents](https://mlsanity.com/paper/2509.25624/) (2025)
- [SentinelNet: Safeguarding Multi-Agent Collaboration Through Credit-Based Dynamic Threat Detection](https://mlsanity.com/paper/2510.16219/) (2025)
- [AgentMark: Utility-Preserving Behavioral Watermarking for Agents](https://mlsanity.com/paper/2601.03294/) (2026)
- [DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors](https://mlsanity.com/paper/2602.05446/) (2026)
- [FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems](https://mlsanity.com/paper/2605.11514/) (2026)
- [Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation](https://mlsanity.com/paper/2606.10749/) (2026)
- [SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants](https://mlsanity.com/paper/2603.28807/) (2026)
- [Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines](https://mlsanity.com/paper/2604.08608/) (2026)
- [Sequential Behavioral Watermarking for LLM Agents](https://mlsanity.com/paper/2605.11036/) (2026)
- [Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety](https://mlsanity.com/paper/2508.03864/) (2025)
- [Clawed and Dangerous: Can We Trust Open Agentic Systems?](https://mlsanity.com/paper/2603.26221/) (2026)
- [Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety](https://mlsanity.com/paper/2607.07097/) (2026)
- [Analyzing Code Injection Attacks on LLM-based Multi-Agent Systems in Software Development](https://mlsanity.com/paper/2512.21818/) (2025)

## Abstract (arXiv)

Multi-agent systems coordinate LLM-based agents to perform tasks on users' behalf. In real-world applications, multi-agent systems will inevitably interact with untrusted inputs, such as malicious Web content, files, email attachments, and more. Using several recently proposed multi-agent frameworks as concrete examples, we demonstrate that adversarial content can hijack control and communication within the system to invoke unsafe agents and functionalities. This results in a complete security breach, up to execution of arbitrary malicious code on the user's device or exfiltration of sensitive data from the user's containerized environment. For example, when agents are instantiated with GPT-4o, Web-based attacks successfully cause the multi-agent system execute arbitrary malicious code in 58-90% of trials (depending on the orchestrator). In some model-orchestrator configurations, the attack success rate is 100%. We also demonstrate that these attacks succeed even if individual agents are not susceptible to direct or indirect prompt injection, and even if they refuse to perform harmful actions. We hope that these results will motivate development of trust and security models for multi-agent systems before they are widely deployed.