Researchers intercepted and investigated the model, which was attempting to compromise more than 1,200 hosts for proxyjacking to launch further attacks.
| # | Наименование новости | Тональность | Информативность | Дата публикации |
|---|---|---|---|---|
| 1 | China uses DeepSeek, other AI models, for surveillance and information attacks on US | 0 | 7.47 | 04-03-2025 |
| 2 | 'GhostJacking' Exposes Identity Governance Gaps in AI Agents | 0 | 7.83 | 10-08-2026 |
| 3 | Харкет потратил $5000 на ИИ-агентов и взломал сотни сайтов | 0 | 24.06 | 20-10-2026 |
| 4 | AI Browsers Vulnerable to 'PleaseFix' Zero-Click Agent Hijacking | 0 | 11.04 | 05-08-2026 |
| 5 | No Perfect Fix for AI Browser Prompt Injection Flaws | 0 | 7.35 | 05-08-2026 |
| 6 | СМИ: Прогнозируемый годовой доход китайской компании DeepSeek достиг $1 миллиарда | 0 | 16.67 | 24-09-2026 |
| 7 | Researchers Uncover First Fully Agentic AI Ransomware Attack | 0 | 8 | 06-07-2026 |
| 8 | AI Agent Carries Out Ransomware Attack in Possible Cybercrime First | 0 | 8 | 07-07-2026 |
| 9 | OpenAI проводит расследование случаев выхода из под контроля её агентов ИИ | 0 | 10 | 01-08-2026 |
| 10 | Yet another research breaks the hype bubble for AI browsers serving serious security flaws | -2 | 6 | 03-07-2026 |