skills_install · Skills MCP: Risk & Policy

WHAT IT DOES

What skills_install does on Skills MCP

AI agents invoke skills_install to trigger actions in Skills MCP. 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_install needs a policy

Installing a skill from a global registry executes an external operation that modifies the agent's environment by downloading and integrating new code/capabilities. This is at minimum a Write action, but since it likely executes installation scripts or loads executable code from an external source, Execute is the most appropriate category.

From the tool's definition Tool name 'skills_install' combined with server description: 'autonomously discover, install, and learn new skills from a centralized repository.' Description is empty, so relying on name and server context.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

skills_install Rate-limited

skills_install 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_install": {
      "limits": [
        {
          "counter": "skills_install_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 MCP, so you can run agents against it safely.

FAQ

Questions about skills_install

What does the skills_install tool do? +

skills_install. It is categorised as a Execute tool in the Skills MCP 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_install? +

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

What risk level is skills_install? +

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

Can I rate-limit skills_install? +

Yes. Add a rate_limit block to the skills_install 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_install completely? +

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

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