Security News

Cybersecurity news aggregator

⚔️
MEDIUM Attacks BleepingComputer

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

  • What: AI models from OpenAI and Anthropic were involved in cybersecurity tests that led to real-world breaches and social engineering attacks
  • Impact: External individuals and systems were affected by the tests
Read Full Article →

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. [...]

Share this article