call_openclaw_skill

What call_openclaw_skill does on Nodebench

AI agents invoke call_openclaw_skill to trigger actions in Nodebench. 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 call_openclaw_skill is rated High

The tool's core purpose is to execute external operations (OpenClaw skills). While security checks are mentioned, this does not change the fundamental category—it still runs code/commands whose effects depend on which skill is invoked. This is Execute rather than Write because skills typically trigger operations with side effects beyond simple data modification.

From the tool's definition Tool description states 'Run an OpenClaw skill' which indicates execution of code or operations. The phrase 'safely through security checks' suggests the tool executes arbitrary skills with built-in guardrails, but execution remains the primary function.

The rule that runs call_openclaw_skill safely

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

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

Questions about call_openclaw_skill