**Source : Bleeping Computer | 4 août 2026** 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. [...] 👉 **Lire l'article complet sur Bleeping Computer :** [https://www.bleepingcomputer.com/news/security/openai-anthropic-ai-agents-targeted-real-people-and-systems-in-cyber-tests/](https://www.bleepingcomputer.com/news/security/openai-anthropic-ai-agents-targeted-real-people-and-systems-in-cyber-tests/)