LAMEHUG Malware Reportedly Integrates Large Language Model for Real-Time Command Generation in a Purported APT28-Linked Cyberattack

July 10, 2025

Ukraine's CERT-UA and Cato CTRL reported LAMEHUG, the first known malware to integrate a large language model (Qwen2.5-Coder-32B-Instruct via Hugging Face) for real-time command generation. Attributed with moderate confidence to APT28 (Fancy Bear), the malware reportedly targeted Ukrainian officials through phishing emails. The LLM is reported to have dynamically generated reconnaissance and data-exfiltration commands executed on infected systems.

The successful integration of a large language model into LAMEHUG malware has significant implications for real-time command generation, highlighting the evolving sophistication of APT28's tactics. As CERT-UA and Cato CTRL reported the incident, it serves as a stark reminder of the importance of robust cybersecurity measures in preventing such attacks. To build on this momentum, experts are working closely with organizations to develop more effective AI governance and harm prevention strategies, ensuring that systems can better resist similar threats in the future, and you can learn more about these efforts by visiting JOIN US.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

Alleged deployer
Fancy Bear, APT28
Alleged developer
hugging face, Alibaba
Alleged harmed parties
Ukrainian government officials, Ukrainian government ministries, State institutions targeted by espionage operations, Public sector information systems, National security and intelligence stakeholders, National cybersecurity infrastructure of Ukraine, Government of Ukraine

AI governance case studies

For forensic AI governance failure analysis (TAIMScore™ case studies), browse Human Signal’s Failure Files™.

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/1220

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.