Researchers at the Hong Kong University of Science and Technology have developed a technique called SkillCloak that allows malicious AI agent skills…
Microsoft has issued a warning about a new attack vector targeting AI agents that use the Model Context Protocol (MCP). Attackers can…
Microsoft has removed 119 malicious extensions from the Edge Add-ons store that used steganography to hide malware in image and font files.…
Koi Security identified the ClawHavoc campaign, which distributed hundreds of malicious skills on the ClawHub marketplace, demonstrating the scale of AI agent…