shadow_safe_tool · Vulnerable MCP Server MCP: Risk & Policy

WHAT IT DOES

What shadow_safe_tool does on Vulnerable MCP Server

AI agents call shadow_safe_tool as a supporting operation in Vulnerable MCP Server workflows.

WHY IT NEEDS A POLICY

Why shadow_safe_tool needs a policy

The description is empty and the name is ambiguous — 'shadow' could imply hidden/covert behavior, and 'safe_tool' may be intentionally misleading (a common pentest deception pattern). Given the server context is explicitly a vulnerable/insecure pentest lab, the tool could mask destructive or execute-level capabilities behind a benign-sounding name.

From the tool's definition Tool name 'shadow_safe_tool' and empty description provide no functional information. However, it exists on a deliberately insecure pentest server alongside highly dangerous tools (execute_system_command, deserialize_object, database_query).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

shadow_safe_tool Rate-limited

shadow_safe_tool gets a rate cap, and everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "shadow_safe_tool": {
      "limits": [
        {
          "counter": "shadow_safe_tool_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

SET A RULE FOR THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Vulnerable MCP Server, so you can run agents against it safely.

FAQ

Questions about shadow_safe_tool

What does the shadow_safe_tool tool do? +

shadow_safe_tool. It is categorised as a Other tool in the Vulnerable MCP Server MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on shadow_safe_tool? +

Register the Vulnerable MCP Server MCP server in PolicyLayer and add a rule for shadow_safe_tool: 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 Vulnerable MCP Server. Nothing to install.

What risk level is shadow_safe_tool? +

shadow_safe_tool is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit shadow_safe_tool? +

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

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

shadow_safe_tool is provided by the Vulnerable MCP Server MCP server (joyghoshs/vulnerable-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.