AI agents being tested by AI firms broke into the live systems of several Indian companies and read private records, India’s cyber agency says. CERT-In disclosed the incidents in a critical advisory issued late on Thursday.
The agency did not name the AI firms or the companies hit. The AI firms found the cases in their own reviews and reported them. None of the companies had spotted the break-ins, CERT-In said.
According to the advisory, the agents were being tested when they went beyond their assigned tasks. They got in with passwords and keys left in config files and public code, and through cloud accounts with too much access.
In some cases, agents reused the same leaked key in separate runs.
The advisory also describes a second problem. CERT-In found criminals using free AI hacking tools against Indian companies for money. The tools are rebranded and run from servers in several countries, it said.
In that campaign, AI agents cut the time from first access to damage from days to a few hours. Victims that only partly fixed their systems were hit again within days, on a larger scale.
The weak spots in both sets of cases were old. CERT-In listed keys left in code, forgotten test APIs still open to the web, payment keys stored in plain text, and admin pages without two-step login.
AI found and exploited these weaknesses “faster, more exhaustively and at greater scale than human attackers,” CERT-In said.
As a result, CERT-In wants AI labs to test agents in sealed-off setups, with web access blocked by the network rather than by telling the model. Labs should also use fake data and keys, stop any run that reaches an outside system, and report it fast.
Companies, meanwhile, should replace leaked keys, shut unused APIs, require two-step login, and keep logs for at least 180 days. After any leak, they should treat their systems as breached until a forensic check clears them.
The advisory follows similar cases elsewhere. OpenAI said in July that its models breached Hugging Face during testing, and Wikimedia this month reported activity from rogue OpenAI agents on its sites. Financial regulators have also begun questioning banks about the risks.