Tiga kerentanan AI berisiko tinggi yang ditemukan di Claude.ai

Kamis, 19 Maret 2026

Dilaporkan oleh AI

Para peneliti telah mengidentifikasi tiga kerentanan berisiko tinggi di Claude.ai. Hal ini memungkinkan rantai serangan ujung ke ujung yang mengeksfiltrasi informasi sensitif tanpa sepengetahuan pengguna. Iklan Google yang sah dapat memicu eksfiltrasi data.

TechRadar melaporkan pada 19 Maret 2026, penemuan tiga kerentanan AI berisiko tinggi di Claude.ai. Cacat tersebut membentuk rantai serangan ujung ke ujung yang mampu menyusupkan informasi sensitif tanpa sepengetahuan pengguna. Khususnya, iklan Google yang sah dapat menyebabkan eksfiltrasi data tersebut. Masalah keamanan ini menyoroti risiko dalam sistem AI di mana elemen eksternal seperti iklan dapat membahayakan data pengguna.

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

Selasa, 07 April 2026 Dilaporkan oleh AI Gambar dihasilkan oleh 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.

Hackers create fake Claude site to spread malware

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.

Claude Mythos leak heightens cyber threats for banks

Jumat, 08 Mei 2026 Dilaporkan oleh 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.

Teknologi

Hackers use AI to exploit security flaws faster, IBM finds

Teknologi

ExpressVPN uncovers 3.7 million leaked AI chatbot data items

Teknologi

OpenClaw AI agents targeted by infostealer malware for first time

Anthropic ends unlimited Claude access via third-party agents, requires extra payments for heavy use

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.

Google report warns of shifting cloud threat landscape

Rabu, 11 Maret 2026 Dilaporkan oleh 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.

BaFin echoes US warnings on Claude Mythos AI risks to banks

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.

AI decodes Facebook ads into personal profiles

Minggu, 10 Mei 2026 Dilaporkan oleh 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.

10 April 2026 01.15

Tiga kerentanan AI berisiko tinggi yang ditemukan di Claude.ai

Artikel Terkait

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

Hackers create fake Claude site to spread malware

Claude Mythos leak heightens cyber threats for banks

Hackers use AI to exploit security flaws faster, IBM finds

ExpressVPN uncovers 3.7 million leaked AI chatbot data items

OpenClaw AI agents targeted by infostealer malware for first time

Anthropic ends unlimited Claude access via third-party agents, requires extra payments for heavy use

Google report warns of shifting cloud threat landscape

BaFin echoes US warnings on Claude Mythos AI risks to banks

AI decodes Facebook ads into personal profiles

US Treasury warns banks of AI cyberattack risks following Anthropic's Claude Mythos announcement

UK study reveals AI agents evading safeguards in user interactions

Infostealers Disguised as Claude Code, OpenClaw, and Other AI Tools

China escalates OpenClaw warnings amid unchecked office adoption

Chinese cybersecurity agency warns of OpenClaw AI risks

Anthropic finds 14 high-severity Firefox flaws using Claude AI

TechRadar: Hackers Use Easy AI Tools for Quicker Cyber Attacks

New cybercrime platform 1Campaign aids malicious Google ads

OpenAI and Google bolster AI safeguards after Grok image scandal

Fake Chrome AI extensions targeted over 300,000 users

Situs web ini menggunakan cookie