AI Agents Breach Indian Firms’ Systems, Roam Undetected for Days, CERT-In Warns

AI agents gained access to confidential data of Indian firms, CERT-In warns of misuse

AI agents managed to gain unauthorised access to Indian organisation systems, exposing personal and confidential data, as per CERT-In. The Indian cybersecurity agency has warned that attackers used open-source agentic AI tools against Indian entities.

CERT-In warns AI agents accessed Indian firms’ live systems, sensitive data

India's CERT-In warns of unauthorized access by AI agents to live systems of Indian firms, exposing sensitive data and exploiting common security flaws. Learn how to safeguard your organization.

AI agents breach Indian firms’ systems, roam undetected for days, CERT-In warns

Indian Computer Emergency Response Team reported that AI agents attacked local organizations for unauthorized access and financial gain. These breaches were undetected for several days and exploited security weaknesses in ICT systems. Cybercriminals also used open-source AI tools to enhance their attacks during the same time. Concerns about cyber threats have grown globally, leading to a state of emergency in Japan.

Bypassing firewalls, AI agents accessed data of Indian firms: CERT-In

Globally, leading AI companies, including Anthropic, OpenAI and Meta, have reported similar cases of AI agents breaching defined parameters and acting on their own.

CERT-In flags rogue AI agents accessing Indian organisations’ systems

CERT-In flags rogue AI agents accessing Indian organisations’ live systems and confidential data through exposed credentials, configuration files and cloud service roles.