AI agents call qflow_task_delete to permanently remove resources in Qflow — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes tasks and their associated data. The cascade parameter indicates it can delete multiple related entities and modify other tasks' dependency references in a single operation. This is clearly destructive as deletions cannot be undone and affect the integrity of the project structure.
From the tool's definition Tool name includes 'delete'; description states '删除任务' (delete task) and explicitly mentions cascade deletion of subtasks and cleanup of dependency references across other tasks
Documented attack patterns abuse exactly the kind of access qflow_task_delete gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Qflow, and nothing reaches the server without passing your rules. This is the rule we recommend for qflow_task_delete:
{
"version": "1",
"default": "deny",
"hide": [
"qflow_task_delete"
]
}qflow_task_delete disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
删除任务。cascade=true 时同时删除子任务，并清理其他任务中的依赖引用。. It is categorised as a Destructive tool in the Qflow MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Qflow MCP server in PolicyLayer and add a rule for qflow_task_delete: 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 Qflow. Nothing to install.
qflow_task_delete 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 qflow_task_delete 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 qflow_task_delete. 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.
qflow_task_delete is provided by the Qflow MCP server (pangu-immortal/qflow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Qflow, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
50 Qflow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.