*sigh* Kali, I thought you were better than this. This Kali Claude AI blog post [1] is again infuriating and the answer of the AI is of course incorrect.

Let's just pretend that all that setup and AI is really worth it to in the end just prompt "do a port scan of scanme.nmap.org".
Claude is running essentially `nmap -sV ...` and it happily reports this (among other ports):
Port 22 - SSH (OpenSSH 6.6.1p1 Ubuntu)

Except if you actually run nmap, the version reported is this:
OpenSSH 6.6.1p1 Ubuntu 2ubuntu2.13 (Ubuntu Linux; protocol 2.0)

That weird string 2ubuntu2.13 is the difference between "omg that version is 10+ years old and has a bunch of vulnerabilities" and "that version has backported security patches and is fine" (probably, I didn't spend much time checking that).

It's just insane that after all that setup they basically run nmap and even that output is questionable. Just learn to read the nmap man page, ffs.

Details matter.

[1] https://www.kali.org/blog/kali-llm-claude-desktop/

#kali #claude #ai

Kali & LLM: macOS with Claude Desktop GUI & Anthropic Sonnet LLM | Kali Linux Blog

This post will focus on an alternative method of using Kali Linux, moving beyond direct terminal command execution. Instead, we will leverage a Large Language Model (LLM) to translate “natural language” descriptions of desired actions into technical commands. Achieving this setup requires the integration of three distinct systems:

Kali Linux
And of course the blog doesn't even mention that everything gets sent to an external API and you just leak all your data ¯\_(ツ)_/¯