nb_review_pending_approvals

What nb_review_pending_approvals does on Nodebench

AI agents call nb_review_pending_approvals to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why nb_review_pending_approvals is rated Low

The tool retrieves data about pending approvals for human review. While it accesses potentially sensitive financial approval information (receipts), it performs no write, destructive, or execute operations. The 'approval-gated' context suggests these are sensitive items, warranting medium severity despite Read category, as misuse could expose confidential receipt/financial data to an AI agent.

From the tool's definition Tool name contains 'review' and description states 'Review approval-gated receipts waiting for a human decision' — indicates querying/retrieving pending approval records for inspection, not modifying them.

The rule that runs nb_review_pending_approvals safely

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

{
  "version": "1",
  "default": "deny",
  "tools": {
    "nb_review_pending_approvals": {}
  }
}

Questions about nb_review_pending_approvals