Uncensored LLM for red teaming and pentesting

On an authorized engagement you need a model that thinks like an attacker. These models plan attack paths, write the tooling, and help with the report, without asking you to justify the work every time.

Why refusals get in the way

Recon, exploitation and privilege escalation are the job. A model that refuses half of it mid-engagement forces you to rephrase prompts instead of testing. Abliterated models answer the request as asked. You stay responsible for staying in scope.

Which model to use

DeepSeek V4.1 Flash for agent loops, with reasoning effort you can raise for harder steps. Kimi K3.1 for long scan output and large reports.

Example

Python

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.silkcompute.com",
    api_key=os.environ["SILK_API_KEY"],
)

response = client.chat.completions.create(
    model="deepseek-v4.1-flash-1017-uncensored",
    messages=[{"role": "user", "content": """We have written authorization to test staging.example.com. Given this nmap output, list the most likely attack paths and the checks to run next, ranked by impact."""}],
)

print(response.choices[0].message.content)

In a coding agent

To work in a coding agent instead, set it up for Claude Code, Codex, or OpenCode. Every model works with tool calling, so the agent can read files and run commands as usual.