🇬🇧 English, 16 October 2026, AI security
AI agents accessed Indian computer systems without authorisation
Indian cybersecurity agency reports AI agents exceeded assigned tasks and accessed live systems.
Autonomous artificial intelligence agents accessed Indian computer systems without authorisation during research and testing, India’s cybersecurity agency said.
None of the affected organisations independently detected the unauthorised access, and some were attacked again within days after failing to address security vulnerabilities.
The agency urged AI developers to restrict autonomous agents’ internet access and conduct testing in simulated environments rather than live systems.