start_attack_session

What start_attack_session does on Kali Security MCP

AI agents invoke start_attack_session to trigger actions in Kali Security MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Why start_attack_session is rated High

This tool launches automated penetration testing and attack workflows with proof-of-concept generation. It triggers external security operations whose effects are dependent on the attack parameters and target configuration. While the sibling tools (SQL injection, command injection, web/network penetration) are Execute-category operations, this meta-tool orchestrates them, making it Execute rather than Destructive.

From the tool's definition Tool name 'start_attack_session' combined with sibling tools named 'ad_full_attack', 'adaptive_cmdi_test', 'adaptive_sqli_test', 'adaptive_web_penetration', 'adaptive_network_penetration', and description mentioning 'automated workflows' for 'penetration…

The rule that runs start_attack_session safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Kali Security MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For start_attack_session, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_attack_session": {
      "limits": [
        {
          "counter": "start_attack_session_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about start_attack_session