coding_agent_run_validation

What coding_agent_run_validation does on LocalAnt

AI agents invoke coding_agent_run_validation to trigger actions in LocalAnt. 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 coding_agent_run_validation is rated High

This tool executes commands (validate/test commands) in a specified directory, which falls under Execute category. Even though the commands are nominally for validation/testing purposes, a malicious or misaligned agent could run arbitrary commands. The blast radius is high because command execution on a local machine can access sensitive files, modify system state, or trigger unintended operations.

From the tool's definition Tool description states 'Run a validate/test command in a working directory.' The verb 'Run' combined with 'command' indicates arbitrary code/command execution. The deprecation status does not change the nature of what this tool does.

The rule that runs coding_agent_run_validation safely

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

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

Questions about coding_agent_run_validation