skills_run_script · Skills MCP: Risk & Policy

WHAT IT DOES

What skills_run_script does on Skills

AI agents invoke skills_run_script to trigger actions in Skills. 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 skills_run_script needs a policy

A 'run_script' tool executes arbitrary or parameterized scripts, which falls squarely into the Execute category. The effect depends entirely on what script is provided as an argument—it could modify state, trigger external operations, or cause side effects. Without explicit constraints limiting it to read-only operations, this poses a high risk if an AI agent calls it with malicious or unintended script content.

From the tool's definition Tool name 'skills_run_script' directly indicates script execution. Sibling tools like 'skills_find_relevant', 'skills_get_asset', 'skills_get_body', 'skills_get_options', 'skills_get_reference', and 'skills_list_all' are all Read operations (search, retrieve,…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

skills_run_script Rate-limited

skills_run_script 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": {
    "skills_run_script": {
      "limits": [
        {
          "counter": "skills_run_script_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 Skills, so you can run agents against it safely.

FAQ

Questions about skills_run_script

What does the skills_run_script tool do? +

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

How do I enforce a policy on skills_run_script? +

Register the Skills MCP server in PolicyLayer and add a rule for skills_run_script: 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 Skills. Nothing to install.

What risk level is skills_run_script? +

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

Can I rate-limit skills_run_script? +

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

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

skills_run_script is provided by the Skills MCP server (jignesh-ponamwar/skills-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.