mlsanityData to 14 Oct 2026

HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing

arXiv 2412.01778 ↗First posted 2 Dec 2024cs.CR cs.AIcited by 37

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

We introduce HackSynth, a novel Large Language Model (LLM)-based agent capable of autonomous penetration testing. HackSynth's dual-module architecture includes a Planner and a Summarizer, which enable it to generate commands and process feedback iteratively. To benchmark HackSynth, we propose two new Capture The Flag (CTF)-based benchmark sets utilizing the popular platforms PicoCTF and OverTheWire. These benchmarks include two hundred challenges across diverse domains and difficulties, providing a standardized framework for evaluating LLM-based penetration testing agents. Based on these benchmarks, extensive experiments are presented, analyzing the core parameters of HackSynth, including creativity (temperature and top-p) and token utilization. Multiple open source and proprietary LLMs were used to measure the agent's capabilities. The experiments show that the agent performed best with the GPT-4o model, better than what the GPT-4o's system card suggests. We also discuss the safety and predictability of HackSynth's actions. Our findings indicate the potential of LLM-based agents in advancing autonomous penetration testing and the importance of robust safeguards. HackSynth and the benchmarks are publicly available to foster research on autonomous cybersecurity solutions.

Key facts. Cited by 37 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 34 of its 53 references that are in the map. First posted on arXiv 2 Dec 2024.

Builds on

34 of 53 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities24 Sep
  2. 2024LLM Agents can Autonomously Hack Websites6 Feb

Other references · 32

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2024GPT-4o System Cardcited by 4,588
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  6. 2023A Survey of Large Language Modelscited by 2,576
  7. 2024Qwen2 Technical Reportcited by 2,120
  8. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  9. 2024Mixtral of Expertscited by 1,823
  10. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  11. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  12. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
20 more
  1. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 1,002
  2. 2024Large Language Models: A Surveycited by 525
  3. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  4. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentationcited by 366
  5. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 260
  6. 2024Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Modelscited by 164
  7. 2023PentestGPT: An LLM-empowered Automatic Penetration Testing Toolcited by 97
  8. 2024AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attackscited by 96
  9. 2024Is Temperature the Creativity Parameter of Large Language Models?cited by 93
  10. 2024NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Securitycited by 93
  11. 2022Lost at C: A User Study on the Security Implications of Large Language Model Code Assistantscited by 91
  12. 2023Impact of Code Language Models on Automated Program Repaircited by 85
  13. 2023Getting pwn'd by AI: Penetration Testing with Large Language Modelscited by 83
  14. 2023Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attackscited by 70
  15. 2024Large Language Models in Cybersecurity: State-of-the-Artcited by 34
  16. 2023Probing the Creativity of Large Language Models: Can models produce divergent semantic association?cited by 33
  17. 2023Decoding the Threat Landscape : ChatGPT, FraudGPT, and WormGPT in Social Engineering Attackscited by 23
  18. 2023How Can ChatGPT Support Human Security Testers to Help Mitigate Supply Chain Attacks?cited by 20
  19. 2023Devising and Detecting Phishing: Large Language Models vs. Smaller Human Modelscited by 17
  20. 2023Can Large Language Models Find And Fix Vulnerable Software?cited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 18; 2026: 19.

37 papers.

Sort:

By area:

  1. 2025VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Frameworkcited by 31
  2. 2025D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Securitycited by 20
  3. 2025A Survey on Agentic Security: Applications, Threats and Defensescited by 20
  4. 2025Benchmarking Practices in LLM-driven Offensive Security: Testbeds, Metrics, and Experiment Designcited by 14
  5. 2025CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Executioncited by 14
  6. 2025A Contemporary Survey of Large Language Model Assisted Program Analysiscited by 11
  7. 2026What Makes a Good LLM Agent for Real-world Penetration Testing?cited by 10
  8. 2025AutoPentest: Enhancing Vulnerability Management With Autonomous LLM Agentscited by 9
  9. 2025RedTeamLLM: an Agentic AI framework for offensive securitycited by 7
  10. 2025PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilitiescited by 7
  11. 2026Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluationcited by 7
  12. 2025Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Huntingcited by 6
25 more
  1. 2025ARACNE: An LLM-Based Autonomous Shell Pentesting Agentcited by 5
  2. 2025Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challengescited by 4
  3. 2025Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teamingcited by 4
  4. 2026Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testingcited by 4
  5. 2025xOffense: An Autonomous Multi-Agent Framework for Penetration Testing with Domain-Adapted Large Language Modelscited by 3
  6. 2026CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarkingcited by 3
  7. 2025Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunitiescited by 2
  8. 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agentscited by 2
  9. 2025Cybersecurity AI: Evaluating Agentic Cybersecurity in Attack/Defense CTFscited by 1
  10. 2026AI In Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomescited by 1
  11. 2026CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environmentscited by 1
  12. 2026Challenges and Future Directions in Agentic Reverse Engineering Systemscited by 1
  13. 2026A Red Teaming Framework for Evaluating Robustness of AI-enabled Security Orchestration, Automation, and Response Systemscited by 1
  14. 2026Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Responsecited by 1
  15. 2025From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testingcited by 0
  16. 2026Environment-Grounded Multi-Agent Workflow for Autonomous Penetration Testingcited by 0
  17. 2026From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-Worldcited by 0
  18. 2026uGen: An Agentic Framework for Generating Microarchitectural Attack PoCscited by 0
  19. 2026Benchmarking Mythos-Linked Bug Rediscoverycited by 0
  20. 2026Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarkscited by 0
  21. 2026StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agentscited by 0
  22. 2026Reveree: Diagnosing LLM Reverse-Engineering Agentscited by 0
  23. 2026Big Enough to Break Out: Tracking the Rising Capability of LLM Penetration-Testing Agentscited by 0
  24. 2026Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural Perspectivescited by 0
  25. 2026No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Baselines Before Architecture: Evaluating Coding Agents for Autonomous Penetration Testing
  2. 2025Construction and Evaluation of LLM-based agents for Semi-Autonomous penetration testing
  3. 2024PentestAgent: Incorporating LLM Agents to Automated Penetration Testing
  4. 2025Vulnerability Mitigation System (VMS): LLM Agent and Evaluation Framework for Autonomous Penetration Testing
  5. 2026APT-Agent: Automated Penetration Testing using Large Language Models
  6. 2025Guided Reasoning in LLM-Driven Penetration Testing Using Structured Attack Trees
  7. 2025Automated Penetration Testing with LLM Agents and Classical Planning
  8. 2025AutoPentester: An LLM Agent-based Framework for Automated Pentesting