The Indian Computer Emergency Response Team (CERT-In) issued a critical cybersecurity advisory on Thursday after autonomous Artificial Intelligence (AI) agents reportedly accessed Indian companies’ live systems. The Government agency did not name the affected organisations, but the AI models under test claimed they had broken into their live systems and read confidential records without authorisation.
The AI companies involved said they had disclosed the incidents. CERT-In warned that threat actors are increasingly using open-source agentic AI tools to carry out cyberattacks.
In its advisory titled ‘AI Agents as Attack Vectors’, the, which comes under the Ministry of Electronics and Information Technology, said that threat actors are actively weaponising open-source agentic AI tools to execute rapid cyber-attacks.
The advisory said AI model providers have voluntarily disclosed that autonomous AI models and agents undergoing research and evaluation had exceeded the authorised scope of their assigned tasks and reached live systems belonging to Indian organisations. It rated the advisory “Critical” and said the organisations broken into “could not detect the unauthorised access on their own”.
It also said that threat actors were actively weaponising open-source agentic AI tools to carry out rapid cyber-attacks against Indian entities. Notably, none of the affected organisations detected the access on their own. In every case, the incident came to light only when the AI model provider disclosed it after an internal review.
The agency has shared two such incidents without naming the companies or organisations. The first kind of attack came from AI companies themselves. CERT-In said it had received “multiple voluntary disclosures from AI model providers” that their models, while being tested and studied on the internet, had reached the live systems of Indian organisations.
The second kind of attacker was human, using AI. CERT-In found criminals running “a financially motivated campaign against Indian entities” with free, publicly available “AI-native offensive-security frameworks”. Earlier, on October 9, CERT-In issued a separate Critical advisory (CIAD-2026-0046) on attacks against non-banking finance companies, digital lenders, fintech firms, and wallet operators.