Microsoft (MSFT) 365 Copilot, the AI tool built into Microsoft Office workplace applications including Word, Excel, Outlook, PowerPoint, and Teams, harbored a critical security flaw that, according to researchers, signals a broader risk of AI agents being hacked, Fortune’s Sharon Goldman reports. The flaw, revealed by AI security startup Aim Security and shared exclusively in advance with Fortune, is the first known “zero-click” attack on an AI agent, an AI that acts autonomously to achieve specific goals. The nature of the vulnerability means that the user doesn’t need to click anything or interact with a message for an attacker to access sensitive information from apps and data sources connected to the AI agent. Microsoft told Fortune that it has already fixed the issue in Microsoft 365 Copilot and that its customers were unaffected.
Confident Investing Starts Here:
- Easily unpack a company's performance with TipRanks' new KPI Data for smart investment decisions
- Receive undervalued, market resilient stocks right to your inbox with TipRanks' Smart Value Newsletter
Published first on TheFly – the ultimate source for real-time, market-moving breaking financial news. Try Now>>
Read More on MSFT:
- Former OpenAI researcher says ChatGPT chooses survival over preventing user harm
- New Copilot flaw signals broader risk of AI agents being hacked, Fortune says
- Quantum stocks higher as Nvidia CEO sees ‘inflection point’
- Morgan Stanley views Google Cloud-OpenAI partnership as ‘important’
- Citi ups Microsoft target, opens ‘upside 90-day catalyst watch’
Looking for a trading platform? Check out TipRanks' Best Online Brokers guide, and find the ideal broker for your trades.
Report an Issue