Tre AI-sårbarheter med hög risk upptäckta i Claude.ai

Forskare har identifierat tre högrisk-sårbarheter i Claude.ai. Dessa möjliggör en end-to-end attackkedja som exfiltrerar känslig information utan användarens vetskap. En legitim Google-annons kan utlösa exfiltrering av data.

TechRadar rapporterade den 19 mars 2026 om upptäckten av tre AI-sårbarheter med hög risk i Claude.ai. Bristerna bildar en end-to-end attackkedja som kan exfiltrera känslig information utan att användaren vet om det. Framför allt kan en legitim Google-annons leda till sådan datautträngning. Denna säkerhetsfråga belyser risker i AI-system där externa element som annonser kan äventyra användardata.

Relaterade artiklar

Illustration of Anthropic restricting Claude Mythos AI and launching Project Glasswing consortium with tech giants to address cybersecurity vulnerabilities.
Bild genererad av AI

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

Rapporterad av AI Bild genererad av AI

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.

Rapporterad av AI

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.

Rapporterad av AI

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.

Rapporterad av AI

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.

 

 

 

Denna webbplats använder cookies

Vi använder cookies för analys för att förbättra vår webbplats. Läs vår integritetspolicy för mer information.
Avböj