skill_run · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What skill_run does on LocalAnt

AI agents invoke skill_run 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 skill_run needs a policy

This tool runs arbitrary enabled skills as subprocesses. While isolation mitigates some risk, execution of untrusted or misaligned skill code can trigger unintended side effects (file changes, network calls, installations, keystrokes).

From the tool's definition 'Run a tool exposed by an enabled skill in an isolated subprocess' — this directly executes code/tools in a subprocess, which is an execution primitive.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

skill_run Rate-limited

skill_run 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": {
    "skill_run": {
      "limits": [
        {
          "counter": "skill_run_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 skill_run

What does the skill_run tool do? +

Run a tool exposed by an enabled skill in an isolated subprocess. 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 skill_run? +

Register the LocalAnt MCP server in PolicyLayer and add a rule for skill_run: 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 skill_run? +

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

Can I rate-limit skill_run? +

Yes. Add a rate_limit block to the skill_run 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 skill_run completely? +

Set action: deny in the PolicyLayer policy for skill_run. 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 skill_run? +

skill_run 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.