# EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities

arXiv: https://arxiv.org/abs/2409.16165 · HTML: https://mlsanity.com/paper/2409.16165/

## Key facts

- Cited by 52 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 17 of its 75 references that are in the map.
- First posted on arXiv 24 Sep 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, 17 of 17)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models](https://mlsanity.com/paper/2408.08926/) (2024)
- [GitHub Copilot AI pair programmer: Asset or Liability?](https://mlsanity.com/paper/2206.15331/) (2022)
- [Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models](https://mlsanity.com/paper/2312.04724/) (2023)
- [Evaluating Frontier Models for Dangerous Capabilities](https://mlsanity.com/paper/2403.13793/) (2024)
- [PentestGPT: An LLM-empowered Automatic Penetration Testing Tool](https://mlsanity.com/paper/2308.06782/) (2023)
- [CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models](https://mlsanity.com/paper/2404.13161/) (2024)
- [CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models](https://mlsanity.com/paper/2408.01605/) (2024)

## Built on by (most cited first, 30 of 52)

- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?](https://mlsanity.com/paper/2410.03859/) (2024)
- [CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale](https://mlsanity.com/paper/2506.02548/) (2025)
- [MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents](https://mlsanity.com/paper/2510.15994/) (2025)
- [HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing](https://mlsanity.com/paper/2412.01778/) (2024)
- [Measuring Agents in Production](https://mlsanity.com/paper/2512.04123/) (2025)
- [D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security](https://mlsanity.com/paper/2502.10931/) (2025)
- [Estimating Worst-Case Frontier Risks of Open-Weight LLMs](https://mlsanity.com/paper/2508.03153/) (2025)
- [Training Language Model Agents to Find Vulnerabilities with CTF-Dojo](https://mlsanity.com/paper/2508.18370/) (2025)
- [Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing](https://mlsanity.com/paper/2512.09882/) (2025)
- [Hacking CTFs with Plain Agents](https://mlsanity.com/paper/2412.02776/) (2024)
- [CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution](https://mlsanity.com/paper/2505.17107/) (2025)
- [SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios](https://mlsanity.com/paper/2509.22097/) (2025)
- [FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents](https://mlsanity.com/paper/2507.15241/) (2025)
- [AutoPentest: Enhancing Vulnerability Management With Autonomous LLM Agents](https://mlsanity.com/paper/2505.10321/) (2025)
- [Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation](https://mlsanity.com/paper/2502.19414/) (2025)
- [AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models](https://mlsanity.com/paper/2506.14682/) (2025)
- [PentestJudge: Judging Agent Behavior Against Operational Requirements](https://mlsanity.com/paper/2508.02921/) (2025)
- [PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities](https://mlsanity.com/paper/2510.11688/) (2025)
- [AutoBaxBuilder: Bootstrapping Code Security Benchmarking](https://mlsanity.com/paper/2512.21132/) (2025)
- [From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization](https://mlsanity.com/paper/2510.02389/) (2025)
- [From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection](https://mlsanity.com/paper/2602.14012/) (2026)
- [OpenSage: Self-programming Agent Generation Engine](https://mlsanity.com/paper/2602.16891/) (2026)
- [CTFusion: A CTF-based Benchmark for LLM Agent Evaluation](https://mlsanity.com/paper/2605.11504/) (2026)
- [The Best Defense is a Good Offense: Countering LLM-Powered Cyberattacks](https://mlsanity.com/paper/2410.15396/) (2024)
- [AgentRec: Agent Recommendation Using Sentence Embeddings Aligned to Human Feedback](https://mlsanity.com/paper/2501.13333/) (2025)
- [Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security](https://mlsanity.com/paper/2507.19399/) (2025)
- [HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities](https://mlsanity.com/paper/2510.12200/) (2025)
- [Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents](https://mlsanity.com/paper/2510.17491/) (2025)
- [KryptoPilot: An Open-World Knowledge-Augmented LLM Agent for Automated Cryptographic Exploitation](https://mlsanity.com/paper/2601.09129/) (2026)

## Abstract (arXiv)

Although language model (LM) agents have demonstrated increased performance in multiple domains, including coding and web-browsing, their success in cybersecurity has been limited. We present EnIGMA, an LM agent for autonomously solving Capture The Flag (CTF) challenges. We introduce new tools and interfaces to improve the agent's ability to find and exploit security vulnerabilities, focusing on interactive terminal programs. These novel Interactive Agent Tools enable LM agents, for the first time, to run interactive utilities, such as a debugger and a server connection tool, which are essential for solving these challenges. Empirical analysis on 390 CTF challenges across four benchmarks demonstrate that these new tools and interfaces substantially improve our agent's performance, achieving state-of-the-art results on NYU CTF, Intercode-CTF, and CyBench. Finally, we analyze data leakage, developing new methods to quantify it and identifying a new phenomenon we term soliloquizing, where the model self-generates hallucinated observations without interacting with the environment. Our code and development dataset are available at https://github.com/SWE-agent/SWE-agent/tree/v0.7 and https://github.com/NYU-LLM-CTF/NYU_CTF_Bench/tree/main/development respectively.