AI agents use send_order_for_approval to create or update resources in Kwork — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kwork environment.
This tool creates or modifies order records on the Kwork marketplace by transitioning an order to an approval state. This is reversible (approval can be withdrawn or orders can be cancelled), making it Write rather than Destructive or Execute. Severity is medium because misuse could cause financial confusion or workflow disruption on the platform, though it doesn't directly move money.
From the tool's definition Tool name 'send_order_for_approval' indicates it modifies order state by submitting an order for approval—a create/modify action on marketplace data. No description provided to clarify scope.
Attacks that exploit this kind of access
send_order_for_approval. It is categorised as a Write tool in the Kwork MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kwork MCP server in PolicyLayer and add a rule for send_order_for_approval: 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 Kwork. Nothing to install.
send_order_for_approval is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the send_order_for_approval 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.
Set action: deny in the PolicyLayer policy for send_order_for_approval. 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.
send_order_for_approval is provided by the Kwork MCP server (simonether/kwork-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →