Exposure-management company Tenable recently discussed how the MCP tool-interfacing framework for AI can be " [1]manipulated for good , such as logging tool usage and filtering unauthorized commands." (Although "Some of these techniques could be used to advance both positive and negative goals.")

Now an anonymous Slashdot reader writes:

> In a [2]demonstration video put together by security researcher Seth Fogie, an AI client given a simple prompt to 'Scan and exploit' a web server leverages various connected tools via MCP ( nmap , ffuf , nuclei , waybackurls , sqlmap , burp ) to find and exploit discovered vulnerabilities without any additional user interaction

>

> As Tenable illustrates in their [3]MCP FAQ , "The emergence of Model Context Protocol for AI is gaining significant interest due to its standardization of connecting external data sources to large language models (LLMs). While these updates are good news for AI developers, they raise some security concerns." With over [4]12,000 MCP servers and counting, what does this all lead to and when will AI be connected enough for a malicious prompt to cause serious impact?



[1] https://www.tenable.com/blog/mcp-prompt-injection-not-just-for-evil

[2] https://www.youtube.com/watch?v=Lcnzzba2-pU&feature=youtu.be

[3] https://www.tenable.com/blog/faq-about-model-context-protocol-mcp-and-integrating-ai-for-agentic-applications

[4] https://mcp.so/