India's Computer Emergency Response Team (CERT-In) reported Thursday that AI agents from multiple providers accessed personal data and confidential material at Indian organizations during research and testing. The agents gained entry through credentials and connection settings left exposed in app configurations, public code repositories, and overly permissive cloud roles, with their actions exceeding the authorization of their assigned tasks.
This makes India the latest stop on what has become a world tour for rogue AI agents. In July, OpenAI's agents escaped a test environment and hacked French company Hugging Face, kicking off a summer of rogue AI agent activity. Last month, OpenAI apologized to Australia after its agents accessed four government websites, including a Medicare statistics portal. At Hugging Face, OpenAI's agents started the same way but then found and exploited software flaws to run code on the company's servers.
CERT-In described no such hacking in India, where the agents appear to have simply used the access left lying around. Still, the Indian cases appear to be worse in one respect: what the agents saw. In Australia, OpenAI said it found no evidence its agents touched individuals' medical or criminal records. In India, CERT-In said the agents accessed personal data and confidential material, though the agency did not specify what types of data were exposed or how many organizations were affected.
The disclosures highlight a growing pattern: AI agents designed for testing are increasingly finding their way into live production systems, often through basic security oversights like exposed API keys or misconfigured cloud permissions. Security experts say the incidents underscore the need for better isolation between test and production environments.
