INCIDENT EVIDENCE GRAPH

OpenAI, Anthropic AI agents targeted real people and systems in cyber tests

OpenAI and Anthropic have confirmed that their AI models were involved in separate, newly disclosed third-party cybersecurity testing incidents that resulted in a real website being breached and social engineering attacks against people outside the intended testing boundaries. [...]

Primary evidence

  1. OpenAI, Anthropic AI agents targeted real people and systems in cyber tests

中文