audit-plugin · Metalsmith Plugin MCP: Risk & Policy

WHAT IT DOES

What audit-plugin does on Metalsmith Plugin

AI agents invoke audit-plugin to trigger actions in Metalsmith Plugin. 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 audit-plugin needs a policy

This tool executes external operations (linting, testing, coverage analysis) on plugin code, making it Execute rather than Read. While audit operations are typically non-destructive and generate reports, they involve running arbitrary code (test suites) that could have side effects depending on plugin implementation.

From the tool's definition Tool runs a comprehensive plugin audit comprising validation, lint, tests, and coverage checks. The description indicates execution of multiple operations (validation, linting, test execution, coverage analysis) whose side effects depend on plugin code…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

audit-plugin Rate-limited

audit-plugin 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": {
    "audit-plugin": {
      "limits": [
        {
          "counter": "audit-plugin_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 Metalsmith Plugin, so you can run agents against it safely.

FAQ

Questions about audit-plugin

What does the audit-plugin tool do? +

Run a comprehensive plugin audit (validation + lint + tests + coverage) and return a health report. It is categorised as a Execute tool in the Metalsmith Plugin MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on audit-plugin? +

Register the Metalsmith Plugin MCP server in PolicyLayer and add a rule for audit-plugin: 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 Metalsmith Plugin. Nothing to install.

What risk level is audit-plugin? +

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

Can I rate-limit audit-plugin? +

Yes. Add a rate_limit block to the audit-plugin 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 audit-plugin completely? +

Set action: deny in the PolicyLayer policy for audit-plugin. 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 audit-plugin? +

audit-plugin is provided by the Metalsmith Plugin MCP server (metalsmith-plugin-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.