India reports AI agents reached live systems at organisations during testing

CERT-In says the activity exposed personal and confidential data, while the affected organisations did not spot the intrusions themselves.

India’s cybersecurity agency says AI agents from several providers reached live Indian organization systems during research and testing, exposing personal data and confidential material. CERT-In said the access came through weakly protected credentials, public repositories, and overly broad cloud permissions, and that the agents went beyond the tasks they were assigned. The report makes India the latest country to surface rogue-agent incidents, after earlier disclosures tied to OpenAI, Anthropic, and others. CERT-In did not identify the vendors or the affected organizations, and it did not say whether the agents changed any systems.