Falla de seguridad de Microsoft Excel permite robo de datos con Copilot

Una vulnerabilidad de seguridad en Microsoft Excel combina hojas de cálculo y el agente Copilot para robar datos potencialmente, según TechRadar. La falla se describe como fascinante en su enfoque. El informe se publicó el 11 de marzo de 2026.

TechRadar ha destacado un problema de seguridad en Microsoft Excel donde las hojas de cálculo se alían con el agente Copilot para facilitar el robo de datos. El título del artículo se refiere a esta vulnerabilidad como «fascinante», lo que sugiere un método de explotación innovador o inesperado. La descripción proporcionada en el informe dice: «Hay más de una manera de despellejar una tabla de Excel», lo que implica usos creativos de las funciones de Excel que van más allá de la funcionalidad estándar. Esto apunta a cómo las capacidades del software podrían ser mal utilizadas en combinación con herramientas de IA como Copilot. No se especifican más detalles técnicos ni plazos en la información disponible, pero la fecha de publicación del artículo es el 11 de marzo de 2026, a las 17:30 UTC. Este descubrimiento subraya las preocupaciones continuas sobre la seguridad de los datos en el software de productividad integrado con agentes de IA.

Artículos relacionados

Dramatic illustration of a computer screen showing OpenClaw AI security warning from Chinese cybersecurity agency, with hacker threats and vulnerability symbols.
Imagen generada por IA

Chinese cybersecurity agency warns of OpenClaw AI risks

Reportado por IA Imagen generada por IA

China's national cybersecurity authority has warned of security risks in the OpenClaw AI agent software, which could allow attackers to gain full control of users' computer systems. The software has seen rapid growth in downloads and usage, with major domestic cloud platforms offering one-click deployment services, but its default security configuration is weak.

Microsoft is developing an always-on version of its AI assistant Copilot that can perform tasks autonomously, drawing inspiration from the OpenClaw platform. The company confirmed early experiments with OpenClaw to enable AI to take actions on users' behalf. Safety measures are a key focus amid concerns over the open-source tool's lack of safeguards.

Reportado por IA

Microsoft has introduced Copilot Health, an AI feature within its Copilot app designed to help users understand their medical records and fitness data. The tool aims to provide context for doctor visits without replacing professional medical advice. It integrates data from wearables and health providers to offer personalized insights.

Following IBM's recent findings on AI accelerating vulnerability exploits, a TechRadar report warns that hackers are turning to accessible AI solutions for faster attacks, often trading off quality or cost. Businesses must adapt defenses to these evolving threats.

Reportado por IA

Hackers are increasingly leveraging artificial intelligence to identify and exploit security vulnerabilities at an accelerated pace. According to a report from IBM, the integration of AI into cyber attacks is speeding up the process significantly. This development highlights evolving threats in cybersecurity.

Security researcher Alexander Hagenah has released an updated tool called TotalRecall Reloaded that reveals weaknesses in Microsoft Windows 11's Recall feature. Despite Microsoft's security overhauls, the tool can intercept user data after Windows Hello authentication without needing administrator privileges. Microsoft maintains that this does not represent a vulnerability.

Reportado por IA

OpenAI has launched Codex Security, a new tool designed to identify cyber risks in companies. It promises to detect complex vulnerabilities that other agentic tools overlook. The tool is available to specific ChatGPT customer tiers.

 

 

 

Este sitio web utiliza cookies

Utilizamos cookies para análisis con el fin de mejorar nuestro sitio. Lee nuestra política de privacidad para más información.
Rechazar