codex_skill_run · Codex MCP: Risk & Policy

WHAT IT DOES

What codex_skill_run does on Codex

AI agents invoke codex_skill_run to trigger actions in Codex. 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 codex_skill_run needs a policy

This tool executes code (Codex skills) as background jobs. Execution of arbitrary or attacker-controlled skills could trigger unauthorized operations, resource consumption, or malicious behavior. It is categorized as Execute rather than Destructive because the tool itself doesn't inherently delete or overwrite data irreversibly; the risk depends on what the skill does.

From the tool's definition Tool name 'codex_skill_run' combined with description 'Run a Codex skill as a BACKGROUND job' indicates execution of arbitrary skills.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

codex_skill_run Rate-limited

codex_skill_run 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": {
    "codex_skill_run": {
      "limits": [
        {
          "counter": "codex_skill_run_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 Codex, so you can run agents against it safely.

FAQ

Questions about codex_skill_run

What does the codex_skill_run tool do? +

Run a Codex skill as a BACKGROUND job. Reads the skill. It is categorised as a Execute tool in the Codex MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on codex_skill_run? +

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

What risk level is codex_skill_run? +

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

Can I rate-limit codex_skill_run? +

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

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

codex_skill_run is provided by the Codex MCP server (pigowenhsiao/codex-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.