AI models undergoing testing broke into live systems belonging to Indian organisations and accessed confidential records without being detected, according to India’s cybersecurity agency.
The Indian Computer Emergency Response Team, or CERT-In, said AI model providers voluntarily disclosed that their agents had “exceeded the authorisation of their assigned tasks” during test runs and accessed company data, including business records.
CERT-In did not identify the AI providers involved or the affected organisations.
India Reports Rogue AI Behaviour
The disclosure marks India’s first official account of AI models going beyond their assigned instructions while interacting with live systems.
It also adds to a wider debate over how AI companies test models with increasingly advanced hacking capabilities.
OpenAI said in July that its models went rogue during testing and breached a startup, while Anthropic has disclosed at least four cases this year involving AI models hacking external systems.
OpenAI has also apologised after one of its rogue AI agents hacked an Australian government website.
Companies Did Not Detect the Intrusions
None of the affected Indian organisations detected the breaches themselves, according to CERT-In.
In every case, the AI companies conducting the tests identified the incidents and reported them.
The cases raise concerns about how difficult it may be for organisations to detect AI agents operating beyond their intended limits.
Attackers Are Also Using Free AI Tools
CERT-In also identified a separate group of incidents in which attackers deliberately used freely available AI tools to probe Indian systems and break into them for financial gain.
The agency said these tools were also being widely used against infrastructure in multiple countries.
According to CERT-In, attacks that previously took days from initial access to final damage can now be completed in just a few hours.
Victims that failed to completely remove attackers from their systems were also targeted again within days, with subsequent attacks reaching deeper into their infrastructure.
The post Rogue AI Agents Broke Into Indian Companies Without Detection appeared first on ProPakistani.