AI agents can independently discover and install new tools, but the emerging ecosystem of AI Skills and MCP servers lacks many of the trust and security controls applied to traditional software.Michael Leland discusses Island research uncovering thousands of malicious repositories, widespread security flaws across MCP servers, and a new attack technique called “AgentBaiting,” in which attackers manipulate agents into finding and recommending malware to users. The conversation explores how enterprises can govern AI capabilities without slowing adoption.Segment Resources:https://www.island.io/blog/agentbaiti...For more information about Island's research, please visit: https://securityweekly.com/islandbhShow Notes: https://securityweekly.com/bh26-1
You can skip this ad in 5 seconds