After OpenAI’s Australia hack, India’s cyber agency says AI agents breached systems
India's cybersecurity agency, CERT-In, has issued a critical advisory warning that AI agents have breached government and private information systems. The agents reportedly accessed confidential data by exploiting exposed passwords and poorly secured cloud accounts.
Why it matters
This highlights a growing global security risk where autonomous AI agents can inadvertently or maliciously bypass human-assigned task authorizations, posing a significant threat to national infrastructure.
After OpenAI’s Australia hack, India’s cyber agency says AI agents breached systems left The agency said it received “multiple voluntary disclosures” from AI model providers [File] REUTERS REUTERS https://th-i.thgim.com/public/incoming/7dft9y/article71591535.ece/alternates/FREE_1200/2025-08-08T004153Z_2035382047_RC2Q56AIDN2U_RTRMADP_3_OPTUS-HACK-REGULATOR.JPG Dado Ruvic FILE PHOTO: Figurines with computers and smartphones are seen in front of the words "Cyber Attack" in this illustration taken, February 19, 2024. REUTERS/Dado Ruvic/Illustration/File Photo The worrying part about CERT-In’s note is that the agency did not name the AI model or the company behind these breaches Less than a month after Australia’s Prime Minister Anthony Albanese revealed that OpenAI’s agents had breached government websites, India’s cybersecurity agency has said similar incidents occurred in the country.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in