openclaw_run_skill · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What openclaw_run_skill does on LocalAnt

AI agents invoke openclaw_run_skill 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 IT NEEDS A POLICY

Why openclaw_run_skill needs a policy

Running a skill (particularly in a system that controls PC operations, shell commands, and browser automation) is an Execute action—it triggers external operations whose effects depend on the skill argument provided. The high severity reflects that skill execution on a local machine could have wide-ranging side effects (file modification, system changes, network access).

From the tool's definition Tool name 'openclaw_run_skill' with verb 'run' indicates execution of arbitrary skills. Server context (LocalAnt) permits shell commands, browser automation, and coding agents.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

openclaw_run_skill Rate-limited

openclaw_run_skill stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches LocalAnt, so you can run agents against it safely.

FAQ

Questions about openclaw_run_skill

What does the openclaw_run_skill tool do? +

${DEPRECATED} Run an OpenClaw skill. It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on openclaw_run_skill? +

Register the LocalAnt MCP server in PolicyLayer and add a rule for openclaw_run_skill: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches LocalAnt. Nothing to install.

What risk level is openclaw_run_skill? +

openclaw_run_skill is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit openclaw_run_skill? +

Yes. Add a rate_limit block to the openclaw_run_skill rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block openclaw_run_skill completely? +

Set action: deny in the PolicyLayer policy for openclaw_run_skill. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides openclaw_run_skill? +

openclaw_run_skill is provided by the LocalAnt MCP server (yuga-hashimoto/localant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.