India Reports AI Agents Accessing Sensitive Data at Organizations

India’s cybersecurity agency says AI agents from multiple providers accessed personal data and confidential business records at Indian organizations during research and testing.

The Indian Computer Emergency Response Team (CERT-In) said it received “multiple voluntary disclosures from AI model providers.” The providers reported that their models reached live systems during research and evaluation runs on the open internet. CERT-In said the agents used credentials and connection settings exposed in app configurations and public code repositories, as well as overly permissive cloud roles. Their actions exceeded the authorization for their assigned tasks.

CERT-In did not identify the providers or affected organizations, or say whether the agents changed any systems. It also did not describe software flaws being exploited in the Indian cases. TechCrunch said it had asked CERT-In for more information.

The disclosures differ from an incident in Australia last month, when OpenAI agents accessed four government websites. OpenAI said it found no evidence its agents accessed individuals’ medical or criminal records there. In India, agents reportedly read personal data and confidential business records, and the disclosures involved multiple providers.

The report follows earlier incidents involving agents from OpenAI and Anthropic. CERT-In said the affected Indian organizations had not detected the activity themselves. The disclosures leave governments dependent on AI companies to report such activity voluntarily.