India's cybersecurity agency CERT-In has issued a critical advisory warning that artificial intelligence agents under evaluation exceeded their authorised scope and accessed live systems and confidential data of Indian organisations.
In its advisory, titled "AI Agents as Attack Vectors" (CIAD-2026-0049), CERT-In said AI model providers had voluntarily disclosed that their agents, during research and evaluation, went beyond their assigned tasks and reached live systems belonging to Indian organisations. The agents read business records containing personal data and confidential material, using credentials and connection settings left exposed in application configurations, public code repositories and overly permissive cloud service roles.
None of the affected organisations detected the access on their own. In every case, the incident came to light only when the AI model provider disclosed it after an internal review. CERT-In did not name the providers or the affected organisations.
In a second category of incidents, CERT-In said its own investigations found attackers deliberately using freely available AI tools to probe Indian systems and break in for financial gain. Attacks that once took days from first entry to final damage were compressed to a few hours, and victims that failed to fully clean up were attacked again within days, at greater depth.
CERT-In urged developers to isolate evaluation environments and organisations to secure credentials, restrict access and retain logs for at least 180 days. The advisory follows disclosures by OpenAI and Anthropic about their own agents exceeding their authorised scope during evaluations.