On this page

Configuration

Cyberstrike uses a simple JSON configuration file to customize its behavior.

Configuration File

Create a cyberstrike.json file in your project directory:

{
  "$schema": "https://cyberstrike.io/schema.json",
  "provider": "anthropic",
  "model": "claude-sonnet-4-20250514",
  "agent": "web-application",
  "tools": ["nmap", "nuclei", "subfinder"]
}

Environment Variables

Set your API keys as environment variables:

Anthropic

export ANTHROPIC_API_KEY="sk-ant-..."

OpenAI

export OPENAI_API_KEY="sk-..."

Google

export GOOGLE_API_KEY="..."

Configuration Options

Option	Type	Default	Description
`provider`	string	`"anthropic"`	AI provider to use
`model`	string	`"claude-sonnet-4-20250514"`	Model identifier
`agent`	string	`"web-application"`	Default agent type
`tools`	array	`[]`	Enabled security tools
`timeout`	number	`300`	Command timeout in seconds
`verbose`	boolean	`false`	Enable verbose logging

Agent-Specific Configuration

Each agent can have its own configuration:

{
  "agents": {
    "web-application": {
      "tools": ["nuclei", "nikto", "sqlmap"],
      "scope": ["*.example.com"]
    },
    "network-pentest": {
      "tools": ["nmap", "masscan"],
      "ports": "1-65535"
    }
  }
}

Tool Configuration

Configure individual tools:

{
  "tools": {
    "nmap": {
      "args": "-sV -sC",
      "timeout": 600
    },
    "nuclei": {
      "templates": ["cves", "vulnerabilities"],
      "severity": ["critical", "high"]
    }
  }
}

Caution

Never commit API keys to version control. Use environment variables or a .env file (added to .gitignore).