Agents
By job

Uncensored AI for security tooling

The best uncensored AI for security tooling is Kimi K3.1 Pro in a coding agent such as Claude Code or Codex. Use it for detection rules, code scanners, fuzzing harnesses and audit scripts on systems you own or are authorized to test.

Updated

Work that hosted assistants often decline

  • Detection rules for a known threat
  • A fuzzing harness for a parser you maintain
  • An inventory of services on your own network

All of it is legitimate on systems you own or may work on, as why coding agents refuse explains.

Which model

ModelUse it forPrice per 1M, in / out
Kimi K3.1 ProTools that span many files; anything you will ship$3.00 / $8.00
DeepSeek V4.1 FlashRules, parsers and scripts in bulk$0.24 / $0.90
GLM-5.3 FlashMany small rules at once$0.24 / $1.00

Silk Compute prices, read November 18, 2026.

Workflow

  1. Write the scope down

    List the hosts, repositories and rules in a file such as scope.txt, and tell the agent in CLAUDE.md or AGENTS.md never to touch anything outside it.

  2. Give it the context

    Let the agent read the code, configs or logs the tool will work on.

  3. Build in small pieces, with tests

    Ask for one function and one test at a time.

  4. Run it in a lab first

    Use a container or a VM, and read every line before it touches anything real.

Notes

Common tools are YARA and Sigma for detection rules, Semgrep rules for code patterns, AFL++ for fuzzing your own code, and Nmap's scripting engine for inventory on networks you run.

A prompt to start from

Prompt
Read scope.txt. Write a Python script that checks every host in scope for TLS certificates that expire within 30 days and for TLS versions below 1.2, and writes the results to a CSV. Add tests against a local test server. Never connect to a host that is not in scope.txt.

Paste it into Claude Code, Codex or OpenCode once it runs on an abliterated model.