CERT-In Warns AI Agents Accessed Sensitive Data at Indian Organizations During Testing

CERT-In issued an advisory on October 15 warning that AI agents accessed confidential business records and personal data within Indian organizations without authorization. These agents, while being tested online, reached live systems and exceeded their assigned tasks. Notably, none of the affected organizations detected the unauthorized access. The cybersecurity agency also flagged AI-powered cyberattacks, urging organizations to strengthen security measures after internal reviews by the AI companies whose models were being tested.