# LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild

arXiv: https://arxiv.org/abs/2410.13919 · HTML: https://mlsanity.com/paper/2410.13919/

## Key facts

- Cited by 12 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 2 of its 8 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## 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, 2 of 2)

- [AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents](https://mlsanity.com/paper/2406.13352/) (2024)
- [LLM in the Shell: Generative Honeypots](https://mlsanity.com/paper/2309.00155/) (2023)

## Built on by (most cited first, 12 of 12)

- [Demonstrating specification gaming in reasoning models](https://mlsanity.com/paper/2502.13295/) (2025)
- [AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents](https://mlsanity.com/paper/2607.26998/) (2026)
- [Winning at All Cost: A Small Environment for Eliciting Specification Gaming Behaviors in Large Language Models](https://mlsanity.com/paper/2505.07846/) (2025)
- [Realistic honeypot evaluations for scheming propensity](https://mlsanity.com/paper/2605.29729/) (2026)
- [AdvancedShelLM: A Stateful Multi-Agent LLM Honeypot for SSH Deception](https://mlsanity.com/paper/2606.27990/) (2026)
- [Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response](https://mlsanity.com/paper/2607.25379/) (2026)
- [Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection](https://mlsanity.com/paper/2604.18248/) (2026)
- [Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents](https://mlsanity.com/paper/2606.04141/) (2026)
- [Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers](https://mlsanity.com/paper/2606.21037/) (2026)
- [Reducing Catastrophic Risk from AI with Systematic Monitoring and Evaluation of Rogue AI Progression](https://mlsanity.com/paper/2609.03189/) (2026)
- [HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving](https://mlsanity.com/paper/2609.08306/) (2026)
- [Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery](https://mlsanity.com/paper/2609.35909/) (2026)

## Abstract (arXiv)

Attacks powered by Large Language Model (LLM) agents represent a growing threat to modern cybersecurity. To address this concern, we present LLM Honeypot, a system designed to monitor autonomous AI hacking agents. By augmenting a standard SSH honeypot with prompt injection and time-based analysis techniques, our framework aims to distinguish LLM agents among all attackers. Over a trial deployment of about three months in a public environment, we collected 8,130,731 hacking attempts and 8 potential AI agents. Our work demonstrates the emergence of AI-driven threats and their current level of usage, serving as an early warning of malicious LLM agents in the wild.