Russian-speaking hackers used SpaceX’s Cursor AI agent to breach a Belgian chemical company and six other firms in recent months, in the latest instance of cybercriminals circumventing AI firms’ safety guardrails.
The hackers recruited the agent for hundreds of attacks by telling it the exercises were part of a simulation, Reuters reported, making their work up to 50% faster.
The agent, powered by an Anthropic model, at one point recommended the hackers use a common malware tool to break into a German manufacturer.
The report comes as OpenAI, Anthropic, Google, and 100 other companies signed an open letter Thursday warning of a “limited window to strengthen cyber defenses” as AI-enabled cyber attacks are set to proliferate in the coming months.