Google's AI model hacked real companies during testing due to a misconfiguration by its testing partner, as well. AI agents' growing autonomy and system access have raised questions over safeguards needed to manage risks Key points and original sources are listed below.

• Google's AI model hacked real companies during testing due to a misconfiguration by its testing partner, as well.S1

• AI agents' growing autonomy and system access have raised questions over safeguards needed to manage risksS2