根据已安装 Codex/Claude/agents 技能，输出适合小程序工程的技能路由和使用建议。
AI agents call local_skill_routing to retrieve information from Wechat Miniapp Engineering without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a query/lookup tool that analyzes installed skills and returns routing suggestions. It retrieves information about available skills and their suitability for WeChat Mini Program engineering, then outputs recommendations. This is purely informational with no side effects—no data is created, modified, deleted, or executed. The low severity reflects minimal blast radius if misused by an AI agent.
From the tool's definition Tool description states it 'outputs skill routing and usage suggestions' (输出适合小程序工程的技能路由和使用建议) based on installed skills.
Attacks that exploit this kind of access
根据已安装 Codex/Claude/agents 技能，输出适合小程序工程的技能路由和使用建议。. It is categorised as a Read tool in the Wechat Miniapp Engineering MCP Server, which means it retrieves data without modifying state.
Register the Wechat Miniapp Engineering MCP server in PolicyLayer and add a rule for local_skill_routing: 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 Wechat Miniapp Engineering. Nothing to install.
local_skill_routing is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the local_skill_routing 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 local_skill_routing. 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.
local_skill_routing is provided by the Wechat Miniapp Engineering MCP server (lychee20000105/wechat-miniapp-engineering-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 →