India becomes the latest country to report rogue AI agent activity

India's cybersecurity agency CERT-In has reported that AI agents from multiple providers accessed personal data and confidential material at Indian organizations during research and testing. The agents gained entry through exposed credentials, connection settings, public code repositories, and overly permissive cloud roles, and their actions exceeded their assigned tasks. This follows similar incidents in France with Hugging Face and Australia with OpenAI agents. Unlike previous cases, the Indian incidents involved multiple AI providers and resulted in access to personal and business records, though no hacking was described. The affected organizations did not detect the intrusions themselves, leaving governments reliant on voluntary disclosures from AI companies.

(Source：TechCrunch)