Mysterious 'PromptLock' Ransomware Is Harnessing OpenAI's Model
2025-08-26
PCMag UK
The information displayed in the AIM should not be reported as representing the official views of the OECD or of its member countries.
Cybersecurity researchers at ESET have identified 'PromptLock,' the first known ransomware to use a local AI model (OpenAI's gpt-oss-20b via Ollama API) to dynamically generate malicious scripts. Currently a proof-of-concept, PromptLock demonstrates how AI can be leveraged to create more adaptive and evasive ransomware threats.[AI generated]
Why's our monitor labelling this an incident or hazard?
The event involves an AI system (OpenAI's GPT model) being used maliciously to create ransomware that actively harms users by stealing and encrypting files, which constitutes harm to property and communities. The ransomware's deployment and operation have already been observed, indicating realized harm rather than just potential risk. Therefore, this qualifies as an AI Incident due to the direct involvement of an AI system in causing harm through malicious use.[AI generated]