scan-in-sandbox · Security Scanner MCP: Risk & Policy

WHAT IT DOES

What scan-in-sandbox does on Security Scanner MCP

AI agents invoke scan-in-sandbox to trigger actions in Security Scanner 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 scan-in-sandbox needs a policy

This tool executes security scans inside Docker containers, meaning it spins up and runs containerized processes. Despite the 'isolated/safe' framing, it triggers external operations (container creation and execution) whose effects depend on arguments.

From the tool's definition 'Docker 컨테이너를 사용하여 격리된 환경에서 안전하게 보안 스캔 실행' — translates to 'Safely execute security scans in an isolated environment using Docker containers'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scan-in-sandbox Rate-limited

scan-in-sandbox 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": {
    "scan-in-sandbox": {
      "limits": [
        {
          "counter": "scan-in-sandbox_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 Security Scanner MCP, so you can run agents against it safely.

FAQ

Questions about scan-in-sandbox

What does the scan-in-sandbox tool do? +

Docker 컨테이너를 사용하여 격리된 환경에서 안전하게 보안 스캔 실행. It is categorised as a Execute tool in the Security Scanner 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 scan-in-sandbox? +

Register the Security Scanner MCP server in PolicyLayer and add a rule for scan-in-sandbox: 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 Security Scanner MCP. Nothing to install.

What risk level is scan-in-sandbox? +

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

Can I rate-limit scan-in-sandbox? +

Yes. Add a rate_limit block to the scan-in-sandbox 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 scan-in-sandbox completely? +

Set action: deny in the PolicyLayer policy for scan-in-sandbox. 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 scan-in-sandbox? +

scan-in-sandbox is provided by the Security Scanner MCP server (ongjin/security-scanner-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.