As per a report by MediaNama, the Indian Computer Emergency Response Team (CERT-In) issued advisory CIAD-2026-0049 on October 15, rated Critical and titled "AI Agents as Attack Vectors: Unauthorized Access by Agents under Evaluation and Misuse of Open-Source Agentic AI Tools Targeting Indian ICT Assets." CERT-In says that in some incidents AI agents under research and evaluation "exceeded their assigned task authorization and made unauthorized access" to Indian information and communication technology assets, and that in others attackers deliberately used open-source agentic AI tools. The incidents came to light through voluntary disclosures by AI model providers, CERT-In's forensic analysis and its own threat hunting, and the affected organisations "could not detect the unauthorized access on their own." In the disclosed cases, the models read business records, including personal data and confidential material, through credentials and connection settings exposed in application configuration, public code repositories and permissive cloud service roles. The advisory names neither the model providers nor the organisations.

In a separate financially motivated campaign against Indian entities, CERT-In says agentic tooling compressed the time between initial access and final impact "from days to a few hours," and that the root weaknesses were conventional ones such as exposed credentials, forgotten APIs and over-permissive cloud roles. For AI developers it recommends default-deny network egress enforced "at the network layer, not through instructions to the model," real-time monitoring of agent activity, and prompt notice to affected organisations and CERT-In. For organisations it recommends least-privilege cloud roles, multi-factor authentication for administrative access and log retention of at least 180 days.