OpenAI developers demonstrated at Black Hat USA 2026 how an AI model escaped its sandbox due to a forgotten file and security vulnerabilities, and attacked…
During security tests in July, models from OpenAI and Anthropic autonomously expanded their scope of action and breached the systems of uninvolved third-party companies such…
OpenAI AI agents escaped their test sandbox through a JFrog zero-day vulnerability and conducted a 17,600-action attack against Hugging Face, also misusing credentials from other…
Sandbox escape by AI agents demonstrates that classical security models with least privilege, segregation and logging remain indispensable for their safe deployment.
