AI Agent Carries Out Multi-Stage Data Theft Attack

Spain’s data protection agency has reported the country’s first agentic AI-powered personal data breach.

Francisco Pérez Bes, president of the Agencia Espanola Proteccion Datos (AEPD), revealed the news in a post on September 14.

He said that an agent using a “known language model” initiated a scan of “generic files” which enabled it to successfully log in.

“Once inside the system, they autonomously began searching for vulnerabilities in the application, which, once found, allowed them to modify personal data and access invoices,” he added.

Read more on agentic threats: Threat Actors Uses Agentic AI to Rapidly Compromise Cloud Target.

Little more is known about the incident until the AEPD investigates the breach notification in more detail. However, it did reveal that the agent was used “as an instrument to successfully chain together different phases of the attack.”

This would imply that it was proactively used by a threat actor rather than went rogue, as per recent incidents revealed by Anthropic and OpenAI.

Simon Phillips, CTO at CybaVerse, argued that such a scenario was troubling as it implies that a threat actor managed to jailbreak or otherwise bypass the guardrails of an advanced model.

“Hopefully we will understand more soon, because organizations need to know what they are facing with AI and where to invest their defenses,” he added. “There is currently too much hype around AI capabilities, and organizations are struggling to understand its impact on their environments. As an industry, we need to put an end to this."

Responding to the AI Threat

Pérez Bes argued that the case marks a watershed moment for the country, with AI evolving from a theoretical to a real-world risk.

AI-assisted or driven attacks must be incorporated into data processing risk analyses, and acceptable response times should be reviewed, he added.

Pérez Bes also argued that the incident highlights the growing importance of digital identities and credentials, and the need for machine-speed incident response.

“The arrival of AI agents in the offensive arena should prompt an immediate review of security and data protection models,” the AEPD concluded.

“Data protection officers, managers, and delegates must prepare for a scenario in which the speed of attacks will increase, but in which the same fundamentals will continue to be crucial: understanding the processing activities, minimizing data, limiting access, correcting vulnerabilities, controlling suppliers and being prepared to respond.”