run_security_test · Sentinel MCP: Risk & Policy

WHAT IT DOES

What run_security_test does on Sentinel

AI agents invoke run_security_test to trigger actions in Sentinel. 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 run_security_test needs a policy

This tool executes security tests (including SQL injection, XSS, SSRF, and authentication bypass attacks) against API endpoints. While security testing is legitimate, the tool's ability to generate and run arbitrary attack payloads means it can trigger code execution, make external requests with malicious inputs, and potentially cause unintended side effects on target systems.

From the tool's definition Tool description states it 'Run[s] OWASP Top 10 2021 security tests on API endpoints' and 'generates attack test cases (SQLi, XSS, SSRF, Auth bypass, IDOR, etc.)'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_security_test Rate-limited

run_security_test 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": {
    "run_security_test": {
      "limits": [
        {
          "counter": "run_security_test_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 Sentinel, so you can run agents against it safely.

FAQ

Questions about run_security_test

What does the run_security_test tool do? +

Run OWASP Top 10 2021 security tests on API endpoints. AI generates attack test cases (SQLi, XSS, SSRF, Auth bypass, IDOR, etc.) and analyzes vulnerabilities. It is categorised as a Execute tool in the Sentinel MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_security_test? +

Register the Sentinel MCP server in PolicyLayer and add a rule for run_security_test: 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 Sentinel. Nothing to install.

What risk level is run_security_test? +

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

Can I rate-limit run_security_test? +

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

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

run_security_test is provided by the Sentinel MCP server (kal72/sentinel-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.