ARACNE: An LLM-Based Autonomous Shell Pentesting Agent
On the map: LLM agents and tool use → Agent threats, guardrails and governance
Abstract (arXiv)
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.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 7 of its 7 references that are in the map. First posted on arXiv 24 Feb 2025.
Builds on
7 of 7 references.
Closest ancestors · 1
Same direction, newest first
Other references · 6
- 2024AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attackscited by 94
- 2024Safeguarding Large Language Models: A Surveycited by 73
- 2024When LLMs Meet Cybersecurity: A Systematic Literature Reviewcited by 70
- 2024PenHeal: A Two-Stage LLM Framework for Automated Pentesting and Optimal Remediationcited by 30
- 2023LLM in the Shell: Generative Honeypotscited by 19
- 2024Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattackscited by 15
Built on by
Citing papers per year: 2025: 2; 2026: 2.
4 papers.
- 2025A Survey on Agentic Security: Applications, Threats and Defensescited by 17
- 2025Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunitiescited by 2
- 2026AdvancedShelLM: A Stateful Multi-Agent LLM Honeypot for SSH Deceptioncited by 1
- 2026StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agentscited by 0
- 2026StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents28 Jul 2026
- 2026AdvancedShelLM: A Stateful Multi-Agent LLM Honeypot for SSH Deception26 Jun 2026
- 2025A Survey on Agentic Security: Applications, Threats and Defenses7 Oct 2025
- 2025Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities8 Sep 2025
Similar, not cited
Close in wording, no citation either way
- 2025RapidPen: Fully Automated IP-to-Shell Penetration Testing with LLM-based Agents
- 2025AutoPentester: An LLM Agent-based Framework for Automated Pentesting
- 2024PentestAgent: Incorporating LLM Agents to Automated Penetration Testing
- 2025AutoPentest: Enhancing Vulnerability Management With Autonomous LLM Agents
- 2026Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural Perspectives
- 2025Construction and Evaluation of LLM-based agents for Semi-Autonomous penetration testing
- 2026APT-Agent: Automated Penetration Testing using Large Language Models
- 2026CARE: Pre-Execution Command Verification for Shell-Executing LLM Agents