将任务拆解为子任务（5 阶段模板），返回 hint 供宿主 LLM 进一步细化。
AI agents use qflow_task_expand to create or update resources in Qflow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Qflow environment.
This tool creates new task structures (subtasks) and modifies the task hierarchy within a project management context. While this is reversible and doesn't delete or execute arbitrary code, it does write/create data artifacts (subtasks and their associated metadata). The medium severity reflects that improper task decomposition could misguide project planning, but the changes are not destructive or irreversible.
From the tool's definition The tool description indicates it 'decomposes tasks into subtasks (5-stage template)' and returns hints. The action of breaking down and structuring tasks into subtasks constitutes creating or modifying project/task data structures in a reversible manner.
Documented attack patterns abuse exactly the kind of access qflow_task_expand 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_expand:
{
"version": "1",
"default": "deny",
"tools": {
"qflow_task_expand": {
"limits": [
{
"counter": "qflow_task_expand_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}qflow_task_expand stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
将任务拆解为子任务（5 阶段模板），返回 hint 供宿主 LLM 进一步细化。. It is categorised as a Write tool in the Qflow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Qflow MCP server in PolicyLayer and add a rule for qflow_task_expand: 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_expand 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 qflow_task_expand 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_expand. 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_expand 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.