Spain reports first data breach involving autonomous AI agent
Spain’s data protection authority (AEPD) has reported its first data breach blamed on an AI agent acting on its own, after the system reportedly logged into a company’s network, found a way to alter personal records, and pulled invoice data.
“Before drawing any conclusions, it should be noted that the available information comes from the notification submitted by the affected organization and will require further analysis,” said Francisco Pérez Bes, deputy director of the AEPD.
Using a specific AI model, he added, doesn’t mean the model or its provider’s infrastructure was compromised, nor that “the tool was designed to carry out malicious activities.”
According to the blog post, the attacking agent started by scanning generic files for weaknesses, then logged in successfully. It searched the target application on its own until it found a flaw, and used that flaw to change personal data and reach invoices.
“This initial notification does not allow us to establish a statistical trend, although it does constitute a significant sign that attacks supported by artificial intelligence have ceased to be a theoretical risk and are beginning to materialize in incidents that affect real processing of personal data,” Pérez Bes noted.
The agency described AI as raising the speed, scale, and capacity to adapt already known malicious techniques, which shrinks the time defenders have to spot and contain an attack.
Spain’s National Cryptologic Center reached a similar conclusion in its guide on offensive AI, calling it an operational capability already built into live campaigns. The guide recommends stronger baseline controls, faster vulnerability management, tighter identity protection, closer oversight of suppliers, and better governance of agent use.
“The arrival of AI agents in the offensive arena should prompt an immediate review of security and data protection models.”
“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,” concluded Pérez Bes.
AI agents test security boundaries
AI-driven attacks have piled up in the headlines over the past few months. According to Google Threat Intelligence Group’s Q3 2026 AI Threat Tracker, threat actors are now automating vulnerability scanning, credential harvesting, and troubleshooting with less human involvement.
In July, Hugging Face, a widely used platform for sharing open-source machine learning models and datasets, disclosed a breach carried out by an autonomous AI agent that had broken out of an internal safety evaluation.
Around the same time, Anthropic disclosed that its Claude models gained unauthorized access to the systems of three organizations during cybersecurity evaluations of their own, after a misconfiguration left the test environment connected to the open internet.
