Field manual · AI for authorized security testing · Edition November 2026 · Updated 2026-11-18

Tool · Apache-2.0

Strix setup: an OpenAI-compatible base URL and a model id

Strix takes a custom model with STRIX_LLM set to openai/<model-id> and LLM_API_BASE set to that API's base URL.

Set STRIX_API_TYPE=chat_completions when the endpoint serves that API. The same variables run Kimi K3.1 Pro or DeepSeek V4.1 Flash.

Updated November 18, 2026Authorized work only
01Fit

When Strix is the right agent

Strix tests a web app, an API or a source tree in a Docker sandbox, and its README calls the agents "autonomous AI hackers that find and fix your app's vulnerabilities." (Strix README) Kimi K3.1 Pro is the pick. Strix's local guide says "Most local models, especially those under 70B parameters, struggle with these complex tasks." (Strix docs)

02Setup

Point Strix at your model

Variable names from the configuration reference, read November 18, 2026.

01

Install Docker, then Strix

The README requires Docker and an LLM key. Strix README.

Installshell
curl -sSL https://strix.ai/install | bash
02

Set the model, the base URL and the API type

STRIX_LLM, LLM_API_BASE and LLM_API_KEY are the three variables, and examples end the base URL in /v1. Configuration reference. Set STRIX_API_TYPE=chat_completions because "A custom LLM_API_BASE does not change this, so set STRIX_API_TYPE=chat_completions when your gateway only serves chat completions."

Kimi K3.1 Proshell
export STRIX_LLM="openai/kimi-k3.1-pro-uncensored"
export LLM_API_BASE="https://api.silkcompute.com/v1"
export LLM_API_KEY="$SILK_API_KEY"
export STRIX_API_TYPE="chat_completions"
export STRIX_REASONING_EFFORT="high"
export STRIX_LLM_INPUT_COST_PER_MTOK="3.00"
export STRIX_LLM_OUTPUT_COST_PER_MTOK="8.00"
export STRIX_LLM_CACHED_INPUT_COST_PER_MTOK="0.3"
strix --target ./app-directory

Model id kimi-k3.1-pro-uncensored. Get a key.

03

Tell Strix what the tokens cost

An unset price counts as 0, so set both if --max-budget should mean anything. The numbers are Silk Compute list prices per 1M tokens, read November 18, 2026.

04

Set reasoning effort

STRIX_REASONING_EFFORT accepts none, minimal, low, medium, high, xhigh and max, and defaults to high. Use max for attack-path analysis. Configuration reference.

05

Name one in-scope target

Pass a directory or a URL you are allowed to test.

One targetshell
strix --target ./app-directory --instruction "Authorized test of this repository only. Stay inside the hosts listed in SCOPE.md."

Strix CLI reference.

Rules of engagement

Only on systems you own, a signed scope, a CTF or a lab. A custom model does not widen the scope.

03Local

A model on your own machine

Ollama uses a different prefix and no /v1. From the local models guide.

Ollamashell
export STRIX_LLM="ollama/<your-model-tag>"
export LLM_API_BASE="http://localhost:11434"
strix --target ./app-directory

Raise Ollama's num_ctx to "at least 16k–32k", or the tool definitions get cut off. Weights that fit one GPU are on local models.

04Prompt

A prompt that stays inside the scope

Prompt

Authorized test. Read SCOPE.md, list the in-scope hosts, the exclusions and the rules, then propose the order of review. Do not write exploit code. Stop if a check is not named in the scope.