security_cve_scan · Infra Ops MCP: Risk & Policy

WHAT IT DOES

What security_cve_scan does on Infra Ops

AI agents invoke security_cve_scan to trigger actions in Infra Ops. 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 security_cve_scan needs a policy

This tool actively executes Trivy, a third-party vulnerability scanner, against a filesystem path. While read-like in intent (scanning/reporting), it runs an external process with effects dependent on the path argument. A malicious or misconfigured path could expose sensitive filesystem areas to scanning, and executing arbitrary external tools on infrastructure carries medium-to-high risk.

From the tool's definition 'Run a CVE vulnerability scan on a filesystem path using Trivy' — executes an external scanning tool (Trivy) against a specified filesystem path

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

security_cve_scan Rate-limited

security_cve_scan 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": {
    "security_cve_scan": {
      "limits": [
        {
          "counter": "security_cve_scan_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 Infra Ops, so you can run agents against it safely.

FAQ

Questions about security_cve_scan

What does the security_cve_scan tool do? +

Run a CVE vulnerability scan on a filesystem path using Trivy. It is categorised as a Execute tool in the Infra Ops MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on security_cve_scan? +

Register the Infra Ops MCP server in PolicyLayer and add a rule for security_cve_scan: 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 Infra Ops. Nothing to install.

What risk level is security_cve_scan? +

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

Can I rate-limit security_cve_scan? +

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

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

security_cve_scan is provided by the Infra Ops MCP server (skyvanguard/infra-ops-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.