run_php

What run_php does on Pentester-MCP

AI agents invoke run_php to trigger actions in Pentester-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 run_php is rated High

run_php executes arbitrary PHP code, which is an Execute category action. Without guardrails on what PHP code can be run, a compromised or misdirected AI agent could execute malicious scripts, access files, or pivot attacks. Severity is high because PHP execution on a web server can compromise systems, but not critical because the tool operates within Docker sandboxing (per server description).

From the tool's definition Tool named 'run_php' on Pentester-MCP server; server description explicitly states it 'enables AI assistants to autonomously execute over 200 open-source penetration testing tools' and includes 'web exploitation' capabilities.

The rule that runs run_php safely

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

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

Questions about run_php