Enterprise deployments of AI agents lean on two extension mechanisms that introduce risk at different layers of the stack. MCP servers expose deterministic code functions with structured, loggable invocations. Skills load textual instruction sets directly into a model’s reasoning context, where their effect depends on conversational state and cannot be enumerated the way source code can. Noma Security’s new whitepaper draws a line between the two and argues that most organizations have governed only the … More →
The post One in four MCP servers opens AI agent security to code execution risk appeared first on Help Net Security.