Delete a question (fails if it is the last one in the form).
AI agents call delete_question to permanently remove resources in Yanifend — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible deletion operation on questionary data. Although it includes a safety check (fails if it is the last question), the core action is permanent data destruction. This is more severe than Write (which is reversible) and falls squarely into the Destructive category.
From the tool's definition Tool name is 'delete_question' and description states 'Delete a question' — this irreversibly removes data from the questionary/feedback widget form.
Attacks that exploit this kind of access
Delete a question (fails if it is the last one in the form). It is categorised as a Destructive tool in the Yanifend MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Yanifend MCP server in PolicyLayer and add a rule for delete_question: 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 Yanifend. Nothing to install.
delete_question 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_question 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_question. 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_question is provided by the Yanifend MCP server (skippedaga/yanifend-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 →