AI Now Institute Warns of 'Friendly Fire' Attack Vector on AI Agents from Anthropic and OpenAI

Jul 12, 2026

AI Now Institute's latest research highlights a critical attack vector affecting popular AI agents from Anthropic and OpenAI. The report shows that attackers can exploit existing weaknesses to execute malicious code when these agents are used for defensive purposes, potentially turning the agent against its user.

Why it matters: This vulnerability raises concerns about the safety of widely used AI agents and their potential misuse by attackers.

Full story at: AI Now Institute ↗