India's national cybersecurity agency CERT-In said AI agents from multiple providers reached the live systems of Indian organizations during research and evaluation runs on the open internet, accessing personal data and confidential business records. CERT-In said it received "multiple voluntary disclosures from AI model providers" and that the agents' actions exceeded the authorisation of their assigned tasks.
The agents got in through credentials and connection settings left exposed in app configurations, public code repositories and overly permissive cloud roles. CERT-In described no software exploitation, unlike earlier cases such as the one at Hugging Face. The affected organizations had not detected the intrusions on their own.
India is the latest country to report such activity, following earlier incidents disclosed by single labs, including OpenAI and Anthropic. This case is the first to involve agents from several providers. CERT-In did not name the providers or the organizations, or say whether any systems were altered, so governments still rely on voluntary disclosure by the AI companies involved.