mlsanityData to 14 Oct 2026

LLMs Killed the Script Kiddie: How Agents Supported by Large Language Models Change the Landscape of Network Threat Testing

arXiv 2310.06936 ↗First posted 10 Oct 2023cs.CR cs.LGcited by 17

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

Abstract (arXiv)

In this paper, we explore the potential of Large Language Models (LLMs) to reason about threats, generate information about tools, and automate cyber campaigns. We begin with a manual exploration of LLMs in supporting specific threat-related actions and decisions. We proceed by automating the decision process in a cyber campaign. We present prompt engineering approaches for a plan-act-report loop for one action of a threat campaign and and a prompt chaining design that directs the sequential decision process of a multi-action campaign. We assess the extent of LLM's cyber-specific knowledge w.r.t the short campaign we demonstrate and provide insights into prompt design for eliciting actionable responses. We discuss the potential impact of LLMs on the threat landscape and the ethical considerations of using LLMs for accelerating threat actor capabilities. We report a promising, yet concerning, application of generative AI to cyber threats. However, the LLM's capabilities to deal with more complex networks, sophisticated vulnerabilities, and the sensitivity of prompts are open questions. This research should spur deliberations over the inevitable advancements in LLM-supported cyber adversarial landscape.

Key facts. Cited by 17 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 23 of its 30 references that are in the map. First posted on arXiv 10 Oct 2023.

Builds on

23 of 30 references.

References · 23

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  8. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  9. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,411
  10. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  11. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  12. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
11 more
  1. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  2. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  3. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  4. 2022GPT-NeoX-20B: An Open-Source Autoregressive Language Modelcited by 713
  5. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 398
  6. 2022Language Models as Agent Modelscited by 132
  7. 2023Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Modelscited by 61
  8. 2023Collaborating with language models for embodied reasoningcited by 61
  9. 2020Linking Threat Tactics, Techniques, and Patterns with Defensive Weaknesses, Vulnerabilities and Affected Platform Configurations for Cyber Huntingcited by 4
  10. 2020Adversarial Genetic Programming for Cyber Security: A Rising Application Domain Where GP Matterscited by 3
  11. 2021Using a Collated Cybersecurity Dataset for Machine Learning and Artificial Intelligencecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 6; 2026: 2.

17 papers.

Sort:

By area:

  1. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
  2. 2024When LLMs Meet Cybersecurity: A Systematic Literature Reviewcited by 71
  3. 2024Large Language Models for Cyber Security: A Systematic Literature Reviewcited by 68
  4. 2023A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Modelscited by 12
  5. 2024Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Searchcited by 12
  6. 2024Hackphyr: A Local Fine-Tuned LLM Agent for Network Security Environmentscited by 9
  7. 2025AutoPentest: Enhancing Vulnerability Management With Autonomous LLM Agentscited by 9
  8. 2025AutoPentester: An LLM Agent-based Framework for Automated Pentestingcited by 6
  9. 2025JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shiftcited by 5
  10. 2026APT-Agent: Automated Penetration Testing using Large Language Modelscited by 2
  11. 2024Decoding BACnet Packets: A Large Language Model Approach for Packet Interpretationcited by 1
  12. 2024Countering Autonomous Cyber Threatscited by 1
5 more
  1. 2025Living Off the LLM: How LLMs Will Change Adversary Tacticscited by 1
  2. 2024TIPS: Threat Actor Informed Prioritization of Applications using SecEncodercited by 0
  3. 2025Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniquescited by 0
  4. 2025From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testingcited by 0
  5. 2026Evaluating Generalization Mechanisms in Autonomous Cyber Attack Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025From Texts to Shields: Convergence of Large Language Models and Cybersecurity
  2. 2024Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities
  3. 2025Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence
  4. 2023Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments
  5. 2026Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies
  6. 2025Benchmarking LLMs in an Embodied Environment for Blue Team Threat Hunting
  7. 2025AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence
  8. 2026Structured but Fragile: On the Limits of LLMs in Cybersecurity Decision-Making