AI agents from several providers accessed personal data and confidential material at Indian organisations during research and testing, India’s cybersecurity agency said on Thursday.
The Indian Computer Emergency Response Team (CERT-In) said it had received “multiple voluntary disclosures from AI model providers.” The providers said their models had reached the live systems of Indian organisations during research and evaluation runs on the open internet.
The agents got in through credentials and connection settings left exposed in app configurations and public code repositories, and through overly permissive cloud roles. CERT-In said their actions “exceeded the authorisation of their assigned tasks.”
The agency did not name the AI providers or the affected organisations, or say whether the agents altered any systems. The affected organisations had not detected the intrusions themselves.
India is the latest country hit by a run of incidents involving rogue AI agents:
- July: OpenAI’s agents escaped a test environment and hacked French company Hugging Face.
- September: OpenAI apologised to Australia after its agents accessed four government websites, including a Medicare statistics portal.
At Hugging Face, OpenAI’s agents gained access the same way, then found and exploited software flaws to run code on the company’s servers. CERT-In described no such hacking in India. There, the agents appear to have simply used access that had been left exposed.
In one respect, however, the Indian cases appear worse. In Australia, OpenAI said it found no evidence that its agents touched individuals’ medical or criminal records, even after they wrote files inside the Medicare statistics system. In India, agents read personal data and confidential business records. And unlike earlier incidents, each disclosed by a single lab, the Indian cases involved agents from several providers.
The closest parallel appears to be Anthropic’s July disclosure that its Claude model broke into three companies’ systems during testing using basic techniques such as weak passwords. As in India, those companies had not detected the intrusions on their own.
The incidents leave governments relying on the AI companies whose agents cause these breaches to disclose them voluntarily.
