# AI-Generated PowerShell Malware: An Experimental Framework and Dataset

arXiv: https://arxiv.org/abs/2606.30819 · HTML: https://mlsanity.com/paper/2606.30819/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 64 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 17 of 17)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022)
- [Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs](https://mlsanity.com/paper/2407.15549/) (2024)
- [A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages](https://mlsanity.com/paper/2410.03981/) (2024)
- [Out of the BLEU: how should we assess quality of the Code Generation models?](https://mlsanity.com/paper/2208.03133/) (2022)
- [An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection](https://mlsanity.com/paper/2406.06822/) (2024)
- [The dark deep side of DeepSeek: Fine-tuning attacks against the safety alignment of CoT-enabled models](https://mlsanity.com/paper/2502.01225/) (2025)
- [AutoPentester: An LLM Agent-based Framework for Automated Pentesting](https://mlsanity.com/paper/2510.05605/) (2025)
- [The Power of Words: Generating PowerShell Attacks from Natural Language](https://mlsanity.com/paper/2404.12893/) (2024)
- [CyberLLMInstruct: A Pseudo-malicious Dataset Revealing Safety-performance Trade-offs in Cyber Security LLM Fine-tuning](https://mlsanity.com/paper/2503.09334/) (2025)
- [AutoMalDesc: Large-Scale Script Analysis for Cyber Threat Research](https://mlsanity.com/paper/2511.13333/) (2025)
- [Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking](https://mlsanity.com/paper/2512.21236/) (2025)
- [RedShell: A Generative AI-Based Approach to Ethical Hacking](https://mlsanity.com/paper/2604.11506/) (2026)
- [Generating Synthetic Malware Samples Using Generative AI](https://mlsanity.com/paper/2604.22084/) (2026)

## Abstract (arXiv)

Generative AI has emerged as a significant cybersecurity threat, with several recent attack campaigns leveraging LLMs to generate code for malicious purposes via scripting languages such as PowerShell. Consequently, for cybersecurity analysts, it is imperative to investigate the offensive capabilities of AI code generators. In this paper, we propose an experimental framework to assess LLM-generated PowerShell malware, which comprises a novel sandbox approach for dynamic analysis of AI-generated malware. Furthermore, we present a novel, manually curated dataset of real-world PowerShell malware, annotated in natural language to assist the training and evaluation of LLMs. Finally, this study evaluates permissive, open-weight LLMs adapted to PowerShell malware generation. Our results reveal a high degree of similarity between real malware and LLM-generated ones in terms of triggered OS malicious events, with a median Jaccard index of 84.5% and 48.4% of instances achieving complete overlap.