For most of the short history of LLM applications, model risk was text risk. A model could output bad advice, leak something from its prompt, or produce a convincing phishing draft — but it couldn't touch your machine. The worst case ended at the screen.
Source: [Dev.to](https://dev.to/correctover/your-agent-has-tools-now-why-mcp-tool-calls-need-runtime-verification-53i6)