March 09, 2026
Recommendations for Securing and Promoting AI Agents
Introduction
AI agents—AI systems that can autonomously plan and execute actions affecting real world systems with minimal human oversight—are poised to transform American productivity and disrupt the technology landscape. Historically, agents completed tasks quickly and humans remained meaningfully in the loop. Now, extended autonomous operations and sprawling agent-to-agent interactions are increasingly common. CNAS welcomes CAISI’s prescient focus on agent-specific security risks.
The core challenge is trust. Many of the underlying security questions are not new. Ensuring secure inputs, monitoring actions, and access control are long-standing concerns for software deployment. But agents introduce distinct and novel challenges. Traditional software executes predefined instructions; agents interpret inputs and select their own actions. Organizations must extend trust beyond a system’s execution to its judgment. The security implications of that shift are significant, and the field lacks mature frameworks for addressing them. Without such frameworks, agent adoption risks a predictable failure mode: it either stalls under excessive caution or advances unchecked until a serious breach forces a disruptive correction.
This response outlines the structural factors that introduce unique security needs for AI agents, the most promising technical and oversight controls, and where further work and government action is most needed.
Download the Full Recommendations
- As a research and policy institution committed to the highest standards of organizational, intellectual, and personal integrity, CNAS maintains strict intellectual independence and sole editorial direction and control over its ideas, projects, publications, events, and other research activities. CNAS does not take institutional positions on policy issues and the content of CNAS publications reflects the views of their authors alone. In keeping with its mission and values, CNAS does not engage in lobbying activity and complies fully with all applicable federal, state, and local laws. CNAS will not engage in any representational activities or advocacy on behalf of any entities or interests and, to the extent that the Center accepts funding from non-U.S. sources, its activities will be limited to bona fide scholastic, academic, and research-related activities, consistent with applicable federal law. The Center publicly acknowledges on its website annually all donors who contribute. ↩
More from CNAS
-
Commentary
Indo-Pacific Security / Technology & National Security
Sharper: China's AI RiseArtificial intelligence has become a strategic priority for Beijing and Washington, yet both countries continue to pursue dramatically different strategies in their bid for gl...
By Charles Horn & Cadence Barker
-
Video
Technology & National Security
UN, Red Cross Call for Rules on Fully Autonomous WeaponsPaul Scharre, executive vice president at the Center for a New American Security, joins CNN to discuss the advent of fully autonomous weapons, the dangers of handing over targ...
By Paul Scharre
-
Commentary
Technology & National Security
Beneath the Surface: Overlooked Cyber Security ThreatsThis article was originally published in War on the Rocks. Cyber security remains a persistent concern for public and private sector organizations alike. Given the potential i...
By Caleb Withers
-
Commentary
Technology & National Security
Why Empowering Private Companies to Fight Cybercrime Had to HappenThere is no question that the government needs to adapt to the reality of the evolving civilianization of the security environment. It should do so boldly, quickly, but carefu...
By Gary Corn
The Center for a New American Security (CNAS) welcomes the opportunity to provide a response to the U.S. Center for AI Standards and Innovation (CAISI) Request For Information: “Security Considerations for Artificial Intelligence Agents.” This submission reflects the views of the following authors1:
- Ben Hayum, Research Assistant, Technology and National Security Program
- Janet Egan, Senior Fellow and Deputy Director, Technology and National Security Program
- Caleb Withers, Research Associate, Technology and National Security Program
With thanks to Paul Scharre, Vivek Chilukuri, Geoffrey Gertz, William L. Anderson, Andy Wang, and Kunyang Li for their valuable feedback.