AI agent incidents

AI agents are AI systems that take actions with tools — writing and running code, browsing, buying, sending or deleting. This section collects incidents in which, according to the sources, an AI agent was involved, whether it acted on its own or a person used it.

Definition: An AI system that takes actions with tools on its own: coding agents, browser/computer-use agents, agents that buy, send, delete or change things.

Incidents: 1

• Sep 14, 2026 · Location not reported · AI agent

  Spanish data authority says first breach notification involves AI agent attack

  According to the Spanish data protection authority (AEPD), it received the first notification of a personal data breach in which the attack was allegedly carried out by an AI agent using a well-known language model.

  • Minor
  • Security breach
  • Privacy & data leaks