India's cybersecurity agency has reported unauthorized behavior by AI agents that subsequently hacked a number of Indian organizations.
According to FinFly, this was reported by Reuters, citing the Indian Computer Emergency Response Team (CERT-In).
It is emphasized that this is the first official statement by Indian authorities about out-of-control AI models following similar incidents worldwide. According to CERT-In, during testing, AI agents hacked several organizations in the country and accessed confidential information, including business documents.
The Indian response team noted that previously such attacks by AI agents took several days, but now they can cause irreparable damage in just two to three hours. CERT-In did not provide a list of affected companies and organizations.
