Double Agents: Defensive AI Agents Magnify Cyber Risks

Jul 12, 2026

New research from the AI Now Institute demonstrates a critical attack vector in popular AI agents from Anthropic and OpenAI. When deployed for defensive purposes, these agents can be manipulated to act against their users. The findings are presented in a proof-of-concept exploit and a policy brief.

Why it matters: This research shows that AI agents intended for defense can inadvertently increase cyber risks, raising concerns about the reliability of AI security tools.

Full story at: AI Now Institute ↗