AI browsers can be hijacked through prompt injection, turning assistants into insider threats. Learn how these exploits work ...
How AI and agentic AI are reshaping malware and malicious attacks, driving faster, stealthier, and more targeted ...
The protocol warned it may pursue criminal and civil action after identifying addresses tied to a hack of its token transfer ...
The indirect prompt injection vulnerability allows an attacker to weaponize Google invites to circumvent privacy controls and ...
RedLine, Lumma, and Vidar adapted in 48 hours. Clawdbot's localhost trust model collapsed, plaintext memory files sit exposed ...
Multiple threat actors, both state-sponsored and financially motivated, are exploiting the CVE-2025-8088 high-severity ...
A drive-by download attack is a type of cyber threat where malicious software is downloaded and installed on a user’s device without their knowledge or consent simply by visiting a compromised or ...
Attackers exploited Hugging Face’s trusted infrastructure to spread an Android RAT, using fake security apps and thousands of ...
Regional APT Threat Situation In December 2025, the global threat hunting system of Fuying Lab detected a total of 24 APT attack activities. These activities were primarily concentrated in regions ...
Ukraine’s CERT says the bug went from disclosure to active exploitation in days Russia-linked attackers are already ...
A high-severity OpenClaw flaw allows one-click remote code execution via token theft and WebSocket hijacking; patched in ...
Russia-linked hacking group Fancy Bear is exploiting a brand-new vulnerability in Microsoft Office, CERT-UA says ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results