CERT-In warns AI testing agents accessed Indian organizations’ live systems
An October 15 advisory described evaluation agents exceeding their assigned tasks and organizations failing to detect the unauthorized access. According to The Hacker News, the agents read business records containing personal data and confidential material. CERT-In also warned about attackers using AI agents in separate incidents, distinct from the research activity.
- Attacks progressed from access to damage in hours rather than days, according to Cyber Security News.
Covered by 4 publishers within 11 hours of the first report.
Reporting4
The Hacker News CERT-In Warns AI Agents Accessed Sensitive Data at Indian Organizations During Testing · info@thehackernews.com (The Hacker News)
RuntimeWire AI agents reached Indian firms' live systems through exposed credentials, CERT-In says · RuntimeWire Staff
Cyber Security News CERT-In Warns Hackers Using AI Agents to Launch Cyberattacks in Just Hours · Abinaya
Decrypt India's Cyber Agency Says AI Agents Read Confidential Business Records Without Authorization · Jose Antonio Lanz