AI agents call feishu_search_user to retrieve information from Lark Cli without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves user information through search—a read-only operation with no ability to modify, delete, or execute actions. The only data returned is a user identifier. While it could potentially facilitate social engineering by mapping names to IDs, the tool itself is purely informational with minimal direct risk. Severity is low due to limited blast radius and reversibility of any information disclosure.
From the tool's definition Tool performs a search operation ('搜索飞书用户' = search Feishu users) by name or email to retrieve user identifiers (open_id). The description explicitly indicates a query/lookup with no modification or side effects.
Attacks that exploit this kind of access
按名字/邮箱搜索飞书用户，拿到 open_id. It is categorised as a Read tool in the Lark Cli MCP Server, which means it retrieves data without modifying state.
Register the Lark Cli MCP server in PolicyLayer and add a rule for feishu_search_user: 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 Lark Cli. Nothing to install.
feishu_search_user 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 feishu_search_user 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 feishu_search_user. 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.
feishu_search_user is provided by the Lark Cli MCP server (yoreland/lark-cli-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 →