Удалить ваше предложение с биржи Kwork.
AI agents call delete_offer to permanently remove resources in Kwork — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes marketplace listings, which is a destructive operation. An AI agent misusing it could delete valuable offers without recovery, damaging the user's freelance business operations. This is severe but scoped to the user's own offers rather than arbitrary data, hence high rather than critical severity.
From the tool's definition delete_offer — permanently deletes a user's offer from the Kwork marketplace. The Russian description confirms this: 'Удалить ваше предложение с биржи Kwork' translates to 'Delete your offer from the Kwork exchange'.
Attacks that exploit this kind of access
Удалить ваше предложение с биржи Kwork. It is categorised as a Destructive tool in the Kwork MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kwork MCP server in PolicyLayer and add a rule for delete_offer: 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.
delete_offer is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_offer 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 delete_offer. 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.
delete_offer 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 →