generate_weevely_agent

What generate_weevely_agent does on Pentester-MCP

AI agents invoke generate_weevely_agent 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 generate_weevely_agent is rated High

Weevely is a penetration testing tool that generates PHP web shells (backdoor agents) for post-exploitation. Even though the description is empty, the tool name and server context make it highly likely this generates a deployable backdoor agent. This falls under Execute (running/generating malicious code artifacts) with critical severity due to the potential for creating persistent access backdoors on target systems.

From the tool's definition Tool name 'generate_weevely_agent' on a pentesting MCP server with sibling tools like 'execute_weevely_module'. Weevely is a well-known web shell generator/backdoor tool used in penetration testing.

The rule that runs generate_weevely_agent 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 generate_weevely_agent, this is the rule to start with:

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

Questions about generate_weevely_agent