Descubiertas tres vulnerabilidades de alto riesgo en Claude.ai

Los investigadores han identificado tres vulnerabilidades de alto riesgo en Claude.ai. Estas vulnerabilidades permiten una cadena de ataque de extremo a extremo que exfiltra información sensible sin el conocimiento del usuario. Un anuncio legítimo de Google podría desencadenar la filtración de datos.

TechRadar informó el 19 de marzo de 2026 del descubrimiento de tres vulnerabilidades de IA de alto riesgo en Claude.ai. Los fallos forman una cadena de ataque de extremo a extremo capaz de exfiltrar información sensible sin que el usuario lo sepa. En concreto, un anuncio legítimo de Google podría conducir a dicha filtración de datos. Este problema de seguridad pone de manifiesto los riesgos de los sistemas de IA en los que elementos externos como los anuncios pueden comprometer los datos de los usuarios.

Artículos relacionados

Illustration of Anthropic restricting Claude Mythos AI and launching Project Glasswing consortium with tech giants to address cybersecurity vulnerabilities.
Imagen generada por IA

Anthropic restricts Claude Mythos AI release and launches Project Glasswing over cybersecurity risks

Reportado por IA Imagen generada por IA

Anthropic has limited access to its Claude Mythos Preview AI model due to its superior ability to detect and exploit software vulnerabilities, while launching Project Glasswing—a consortium with over 45 tech firms including Apple, Google, and Microsoft—to collaboratively patch flaws and bolster defenses. The announcement follows recent data leaks at the firm.

Cybersecurity researchers have identified a fraudulent website mimicking the popular AI tool Claude that delivers backdoor malware to visitors. The discovery highlights how cybercriminals are capitalizing on growing interest in artificial intelligence platforms.

Reportado por IA

Anthropic's latest AI model Claude Mythos has leaked despite being deemed too dangerous for public release. Financial institutions now face advanced AI-powered attacks capable of exploiting unknown vulnerabilities.

Anthropic has restricted unlimited access to its Claude AI models through third-party agents like OpenClaw, requiring heavy users to pay extra via API keys or usage bundles starting April 4, 2026. The policy shift, announced over the weekend, addresses severe system strain from high-volume agent tools previously covered under $20 monthly subscriptions.

Reportado por IA

A new Google research report indicates that the cloud security threat landscape is rapidly evolving. Hackers are increasingly targeting third parties and software vulnerabilities to breach systems. The report also notes a decline in cloud misconfigurations.

Germany's financial regulator BaFin has warned banks about risks from Anthropic's Claude Mythos AI model, following US Treasury alerts. The model autonomously detects IT vulnerabilities at scale, potentially accelerating cyberattacks. US banks are testing it amid restrictions.

Reportado por IA

Artificial intelligence can now extract full personal profiles from Facebook advertisements more quickly and affordably than expected. Harmless ads appear to carry enough data for detailed identity mapping.

 

 

 

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