Researchers Discover First AI-Powered Ransomware Dubbed "PromptLock"
The malware uses a large language model to generate malicious scripts, highlighting a new class of AI-driven security threats.
The security threat landscape for artificial intelligence evolved significantly on Aug. 26, 2025, with the discovery of what researchers are calling the first AI-powered ransomware. The new malware, named "PromptLock," demonstrates how an organization's own AI tools can be turned against it, validating rising concerns among cybersecurity leaders.
How PromptLock Works
Cybersecurity firm ESET reported the discovery of PromptLock, a piece of malware written in the Go programming language. It functions as a hard-coded prompt injection attack, using an open-source API called Ollama to interface with a locally run large language model.
By sending malicious prompts, the malware instructs …
Archive Access
This article is older than 24 hours. Create a free account to access our 7-day archive.