PoeLLM Malware Infects 3,400+ Servers to Expand Crypto Mining Botnet
PoeLLM malware targets AI/LLM infrastructure to expand crypto mining botnet.
A new malware family named PoeLLM, part of the Canto Incognito campaign, is targeting exposed AI and LLM infrastructure to deploy cryptocurrency miners like XMRig and Iron. The malware uses a novel technique to hide its C2 address within a poem hosted on GitHub. Over 3,400 servers have been infected, primarily in the U.S. and Western Europe, with compromised hosts repurposed to scan for and infect additional vulnerable systems.
AI summary of the linked source. Not reviewed by an editor. How this works
Run Lumen?
Get an email when a new story names Lumen, usually within the hour.
Free. Your list stays private and never appears in a subject line. One click stops it. How Vendor Watch worksPrivacy
The lesson from this incident
Full lessonThe PoeLLM malware campaign highlights the critical risk of leaving AI and LLM infrastructure publicly exposed without proper hardening or access controls. Attackers exploited misconfigured or insufficiently secured servers to deploy cryptocurrency miners, effectively stealing compute resources at scale. A novel C2 obfuscation technique — hiding command-and-control addresses inside a poem on GitHub — demonstrates how adversaries are evolving to evade traditional detection methods. Compromised servers were then weaponized to propagate the botnet further, amplifying the damage exponentially. This attack underscores that emerging AI infrastructure carries the same — if not greater — attack surface risks as traditional systems and must be treated accordingly.
What helps against this
How we list vendors- Vulnerability scanning and prioritisation
You know which systems are vulnerable, and which ones to fix first.
- Cyber asset inventory
You cannot patch, monitor or protect the devices, cloud resources and accounts you do not know you have.
- Endpoint detection and response (EDR and XDR)
Malware and hands-on-keyboard attackers on laptops and servers get spotted and stopped.
Indicators of Compromise
Extracted by AI from the linked source. Not reviewed by an editor. How this works
- malware — PoeLLM
- malware — XMRig
- malware — Iron