superskills_run · Superskills MCP: Risk & Policy

WHAT IT DOES

What superskills_run does on Superskills

AI agents invoke superskills_run to trigger actions in Superskills. 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 superskills_run needs a policy

This tool appears designed to execute code or commands on the local system. While the empty description limits confidence slightly, the tool name 'run' paired with a 'general-purpose MCP gateway' for 'local CLI skills' indicates arbitrary code execution capability.

From the tool's definition Tool name 'superskills_run' combined with server purpose ('exposes your local CLI skills to any AI assistant') and the presence of sibling tools like 'superskills_invoke' strongly suggest execution of arbitrary CLI commands or local scripts.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

superskills_run Rate-limited

superskills_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": {
    "superskills_run": {
      "limits": [
        {
          "counter": "superskills_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 Superskills, so you can run agents against it safely.

FAQ

Questions about superskills_run

What does the superskills_run tool do? +

superskills_run. It is categorised as a Execute tool in the Superskills MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on superskills_run? +

Register the Superskills MCP server in PolicyLayer and add a rule for superskills_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 Superskills. Nothing to install.

What risk level is superskills_run? +

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

Can I rate-limit superskills_run? +

Yes. Add a rate_limit block to the superskills_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 superskills_run completely? +

Set action: deny in the PolicyLayer policy for superskills_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 superskills_run? +

superskills_run is provided by the Superskills MCP server (lee2026-dev/superskills-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.