We introduce ARACNE, a fully autonomous LLM-based pentesting agent tailored for SSH services that can execute commands on real Linux shell systems. Introduces a new agent architecture with multi-LLM model support. Experiments show that ARACNE can reach a 60\% success rate against the autonomous defender ShelLM and a 57.58\% success rate against the Over The Wire Bandit CTF challenges, improving over the state-of-the-art. When winning, the average number of actions taken by the agent to accomplish the goals was less than 5. The results show that the use of multi-LLM is a promising approach to increase accuracy in the actions.
@article{arxiv.2502.18528,
title = {ARACNE: An LLM-Based Autonomous Shell Pentesting Agent},
author = {Tomas Nieponice and Veronica Valeros and Sebastian Garcia},
journal= {arXiv preprint arXiv:2502.18528},
year = {2025}
}