AI agents use publish_text_card to create or update resources in Xhs Kit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xhs Kit environment.
This tool creates and publishes new content (text-based card notes) to a social media platform, which is a reversible write operation. It modifies platform state by adding new user-generated content. Severity is high because malicious agents could spam, post misleading information, or manipulate audience engagement at scale.
From the tool's definition Tool name 'publish_text_card' and description '发布文字配图笔记(将文字生成为卡片图片)' [publish text card notes (generate text as card images)] indicates creation and posting of content to Xiaohongshu platform.
Attacks that exploit this kind of access
发布文字配图笔记(将文字生成为卡片图片). It is categorised as a Write tool in the Xhs Kit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xhs Kit MCP server in PolicyLayer and add a rule for publish_text_card: 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 Xhs Kit. Nothing to install.
publish_text_card 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_text_card 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_text_card. 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_text_card is provided by the Xhs Kit MCP server (luweizheng/xhs-kit). 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 →