Spain's data regulator receives first breach notification for an attack run by an AI agent
Spain's data protection agency (AEPD) disclosed it had received the first notification of a personal-data breach reportedly carried out through an AI agent using a well-known language model. According to the affected organisation's notification, the agent searched generic files for vulnerabilities, logged in successfully, then autonomously probed the application until it could modify personal data and access invoices.
The AEPD stressed that the information comes from the affected organization's notification and still has to be analysed, and that use of a particular model does not mean the model or its provider was compromised. It called the case a sign that AI-executed attacks are no longer theoretical.
What would have stopped it
Fast vulnerability management and anomaly detection that operate at machine speed would have limited what the attacking agent could reach.
Guardrails
- G1 Least privilege Not assessed Did the agent hold only the access the task needed?
- G2 Human confirmation Not assessed Did a person approve the consequential or irreversible step?
- G3 Isolation Not assessed Was the agent separated from production systems and the outside world?
- G4 Instruction integrity Failed The model's agent carried out an attacker's intrusion steps.
- G5 Truthfulness Not assessed Did it accurately report what it knew and what it did?
- G6 Limits Not assessed Was there a cap on rate, spend, volume or scale?
- G7 Oversight Not assessed Could a responsible human see what it was doing and stop it in time?
- G8 Recovery Not assessed Could the damage be undone?
Sources
-
“La Agencia Española de Protección de Datos ha recibido la primera notificación de una brecha de datos personales en la que el incidente habría sido ejecutado mediante un agente de inteligencia artificial que utilizó un conocido modelo de lenguaje.”
-
“Una vez dentro del sistema, el agente de IA continuó de forma autónoma buscando fallos en la aplicación hasta encontrar una vía que le permitió modificar información personal y acceder a facturas.”
-
“The Spanish Data Protection Agency (AEPD) has published details of the first notification of a personal data protection breach executed by design through an AI agent.”
Confidence 94% comes from these sources alone. How we score
History
- 14 Oct 2026Entered in the register with 3 sources