The Dark Side of LLMs Agent-based Attacks for Complete Computer Takeover
Authors:
- Luigi ArenaLALuigi Arena
Preprint
Abstract
The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables unprecedented capabilities in natural language processing and generation. However, these systems have introduced unprecedented security vulnerabilities that extend beyond traditional prompt injection attacks. This paper presents the first comprehensive evaluation of LLM agents as attack vectors capable of achieving complete computer takeover through the exploitation of trust boundaries within agentic AI systems where autonomous entities interact and influence each other. We demonstrate that adversaries can leverage three distinct attack surfaces - direct prompt injection, RAG backdoor attacks, and inter-agent trust exploitation - to coerce popular LLMs (including GPT-4o, Claude-4 and Gemini-2.5) into autonomously installing and executing malware on victim machines. Our evaluation of 17 state-of-the-art LLMs reveals an alarming vulnerability hierarchy: while 41.2% of models succumb to direct prompt injection, 52.9% are vulnerable to RAG backdoor attacks, and a critical 82.4% can be compromised through inter-agent trust exploitation. Notably, we discovered that LLMs which successfully resist direct malicious commands will execute identical payloads when requested by peer agents, revealing a fundamental flaw in current multi-agent security models. Our findings demonstrate that only 5.9% of tested models (1/17) proved resistant to all attack vectors, with the majority exhibiting context-dependent security behaviors that create exploitable blind spots. Our findings also highlight the need to increase awareness and research on the security risks of LLMs, showing a paradigm shift in cybersecurity threats, where AI tools themselves become sophisticated attack vectors.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- TRiSM for Agentic AI: A review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent SystemsAI Open, 2026
- The Emerged Security and Privacy of LLM Agent: A Survey with Case StudiesACM Computing Surveys, 2025
- CyberRAG: An agentic RAG cyber attack classification and reporting toolFuture Generation Computer Systems, 2025
- The rise and potential of large language model based agents: a surveyScience China Information Sciences, 2025
- AGENTVIGIL: Automatic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents2025
- Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents2024
- AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases2024
- Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection2024
- Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning2021
- Weight Poisoning Attacks on Pretrained Models2020