audit_code · Vending Machine MCP: Risk & Policy

WHAT IT DOES

What audit_code does on Vending Machine

AI agents invoke audit_code to trigger actions in Vending Machine. 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_code needs a policy

The tool runs an automated security audit pipeline involving multiple specialist agents (Bug Hunter, Test Goblin, etc.). This constitutes executing an external multi-step process against potentially sensitive code. While it is primarily analytical/read in intent, it triggers active agent execution pipelines whose side effects depend on the code submitted.

From the tool's definition 'Full security audit pipeline: Bug Hunter finds vulnerabilities, Test Goblin' — triggers a multi-agent pipeline execution against code

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

audit_code Rate-limited

audit_code 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_code": {
      "limits": [
        {
          "counter": "audit_code_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 Vending Machine, so you can run agents against it safely.

FAQ

Questions about audit_code

What does the audit_code tool do? +

Full security audit pipeline: Bug Hunter finds vulnerabilities, Test Goblin. It is categorised as a Execute tool in the Vending Machine 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_code? +

Register the Vending Machine MCP server in PolicyLayer and add a rule for audit_code: 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 Vending Machine. Nothing to install.

What risk level is audit_code? +

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

Can I rate-limit audit_code? +

Yes. Add a rate_limit block to the audit_code 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_code completely? +

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

audit_code is provided by the Vending Machine MCP server (yokiidesu/vending-machine-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.