hooks_post-command

What hooks_post-command does on Claude Flow

AI agents use hooks_post-command to create or update resources in Claude Flow, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Flow environment.

Why hooks_post-command is rated Medium

This tool creates or modifies records of command execution outcomes, which is a reversible write operation. It does not execute commands itself (Execute category) nor delete data (Destructive). Severity is medium because malicious recording could falsify audit logs or create misleading execution records in an enterprise system, but the primary impact is data modification rather than direct system compromise.

From the tool's definition Tool name 'hooks_post-command' and description 'Record command execution outcome' indicate it writes/records data about executed commands. The incomplete description mentions 'native Bash hooks' suggesting integration with command execution pipelines.

The rule that runs hooks_post-command safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For hooks_post-command, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "hooks_post-command": {
      "limits": [
        {
          "counter": "hooks_post-command_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about hooks_post-command