NIST Seeks Input on AI Agent Security Risks

• •NIST's CAISI has launched an RFI to address AI agent security challenges.
• •AI agent systems face unique risks, including adversarial data and model insecurity.
• •Responses to the RFI are due by March 9, 2026, to inform future security guidelines.

The Center for AI Standards and Innovation (CAISI) at NIST has issued a Request for Information (RFI) to gather insights on securing AI agent systems. These systems, capable of autonomous actions, face unique security challenges, including risks from adversarial data and insecure models. The RFI aims to address security threats that may hinder the adoption of AI agents and pose risks to public safety and national security. Stakeholders from industry, academia, and the security community are encouraged to provide examples and recommendations. The RFI will inform future guidelines and best practices for AI agent security, with responses due by March 9, 2026. The initiative is part of a broader effort to establish standards and protocols for secure AI agent deployment.