# LLM in the Shell: Generative Honeypots

arXiv: https://arxiv.org/abs/2309.00155 · HTML: https://mlsanity.com/paper/2309.00155/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 23 references that are in the map.
- First posted on arXiv 31 Aug 2023.

## Builds on (most cited first, 4 of 4)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Chatbots in a Honeypot World](https://mlsanity.com/paper/2301.03771/) (2023)

## Built on by (most cited first, 19 of 19)

- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [When LLMs Meet Cybersecurity: A Systematic Literature Review](https://mlsanity.com/paper/2405.03644/) (2024)
- [Large Language Models in Cybersecurity: State-of-the-Art](https://mlsanity.com/paper/2402.00891/) (2024)
- [AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents](https://mlsanity.com/paper/2509.07764/) (2025)
- [LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild](https://mlsanity.com/paper/2410.13919/) (2024)
- [LLM Honeypot: Leveraging Large Language Models as Advanced Interactive Honeypot Systems](https://mlsanity.com/paper/2409.08234/) (2024)
- [Advancing Autonomous Incident Response: Leveraging LLMs and Cyber Threat Intelligence](https://mlsanity.com/paper/2508.10677/) (2025)
- [ARACNE: An LLM-Based Autonomous Shell Pentesting Agent](https://mlsanity.com/paper/2502.18528/) (2025)
- [Toward Intelligent and Secure Cloud: Large Language Model Empowered Proactive Defense](https://mlsanity.com/paper/2412.21051/) (2024)
- [VelLMes: A high-interaction AI-based deception framework](https://mlsanity.com/paper/2510.06975/) (2025)
- [SBASH: a Framework for Designing and Evaluating RAG vs. Prompt-Tuned LLM Honeypots](https://mlsanity.com/paper/2510.21459/) (2025)
- [AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents](https://mlsanity.com/paper/2607.26998/) (2026)
- [Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots](https://mlsanity.com/paper/2605.29963/) (2026)
- [One Goal, Many Commands: Characterizing Denylist Fragility in AI Agents](https://mlsanity.com/paper/2606.15549/) (2026)
- [AdvancedShelLM: A Stateful Multi-Agent LLM Honeypot for SSH Deception](https://mlsanity.com/paper/2606.27990/) (2026)
- [ShIOEnv: A Command Evaluation Environment for Grammar-Constrained Synthesis and Execution Behavior Modeling](https://mlsanity.com/paper/2505.18374/) (2025)
- [Design and Development of an Intelligent LLM-based LDAP Honeypot](https://mlsanity.com/paper/2509.16682/) (2025)
- [Towards Agentic Honeynet Configuration](https://mlsanity.com/paper/2603.14122/) (2026)
- [HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving](https://mlsanity.com/paper/2609.08306/) (2026)

## Abstract (arXiv)

Honeypots are essential tools in cybersecurity for early detection, threat intelligence gathering, and analysis of attacker's behavior. However, most of them lack the required realism to engage and fool human attackers long-term. Being easy to distinguish honeypots strongly hinders their effectiveness. This can happen because they are too deterministic, lack adaptability, or lack deepness. This work introduces shelLM, a dynamic and realistic software honeypot based on Large Language Models that generates Linux-like shell output. We designed and implemented shelLM using cloud-based LLMs. We evaluated if shelLM can generate output as expected from a real Linux shell. The evaluation was done by asking cybersecurity researchers to use the honeypot and give feedback if each answer from the honeypot was the expected one from a Linux shell. Results indicate that shelLM can create credible and dynamic answers capable of addressing the limitations of current honeypots. ShelLM reached a TNR of 0.90, convincing humans it was consistent with a real Linux shell. The source code and prompts for replicating the experiments have been publicly available.