AI agents use publish_task to create or update resources in Xingzi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xingzi environment.
This tool creates new marketing tasks on the Xingzi platform with associated financial parameters (unit pricing, participant count), making it a Write operation. It does not execute arbitrary code or trigger external operations based on dynamic arguments (Execute), nor does it irreversibly delete data (Destructive).
From the tool's definition Tool description states '发布代发任务（核心操作）' (publish distribution task - core operation), explicitly involves uploading material files ('上传素材文件'), setting task requirements ('写清任务要求'), and configuring pricing and participant numbers ('设置单价和人数').
Attacks that exploit this kind of access
发布代发任务（核心操作）。上传素材文件，写清任务要求，设置单价和人数，KOC 就会来领取。 默认：常规素材 + 固定单价 + 星子代发平台 + 公开 + 所有人可见。 单价建议 ≥ 5 元/条。. It is categorised as a Write tool in the Xingzi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xingzi MCP server in PolicyLayer and add a rule for publish_task: 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 Xingzi. Nothing to install.
publish_task 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 publish_task 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 publish_task. 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.
publish_task is provided by the Xingzi MCP server (yylwdyx-commits/xingzi-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 →