waf_run_self_tests · Hospital WAF MCP: Risk & Policy

WHAT IT DOES

What waf_run_self_tests does on Hospital WAF MCP

AI agents invoke waf_run_self_tests to trigger actions in Hospital WAF 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 waf_run_self_tests needs a policy

This tool executes pre-defined security test payloads against the WAF engine. While the payloads are curated samples rather than arbitrary code, the tool triggers execution of attack vectors (SQL injection, XSS, command injection, path traversal) through the system.

From the tool's definition Tool description states it 'runs built-in SQLi/XSS/command injection/path traversal samples' (translated from Chinese: '运行内置 SQLi/XSS/命令注入/路径遍历样例'). The term '运行' (run) and the reference to executing test payloads indicates code/command execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

waf_run_self_tests Rate-limited

waf_run_self_tests 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": {
    "waf_run_self_tests": {
      "limits": [
        {
          "counter": "waf_run_self_tests_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 Hospital WAF MCP, so you can run agents against it safely.

FAQ

Questions about waf_run_self_tests

What does the waf_run_self_tests tool do? +

运行内置 SQLi/XSS/命令注入/路径遍历样例，用于快速验证引擎是否检出攻击。. It is categorised as a Execute tool in the Hospital WAF 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 waf_run_self_tests? +

Register the Hospital WAF MCP server in PolicyLayer and add a rule for waf_run_self_tests: 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 Hospital WAF MCP. Nothing to install.

What risk level is waf_run_self_tests? +

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

Can I rate-limit waf_run_self_tests? +

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

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

waf_run_self_tests is provided by the Hospital WAF MCP server (12211725-star/hospital-waf-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.