【批量删除·谨慎调用】使用统一数组接口批量删除多个文件或目录。
AI agents call delete_files to permanently remove resources in LuzzyTool — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes files and directories without reversibility, meeting the Destructive category definition. The batch nature and directory deletion capability increase severity to critical due to potential for catastrophic data loss if an AI agent misuses wildcard patterns or targets system directories.
From the tool's definition Tool name is 'delete_files' and description states '批量删除·谨慎调用' (batch delete - use with caution) with capability to delete multiple files or directories. The warning label and plural scope indicate irreversible data loss operations.
Attacks that exploit this kind of access
【批量删除·谨慎调用】使用统一数组接口批量删除多个文件或目录。. It is categorised as a Destructive tool in the LuzzyTool MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the LuzzyTool MCP server in PolicyLayer and add a rule for delete_files: 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 LuzzyTool. Nothing to install.
delete_files is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_files 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 delete_files. 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.
delete_files is provided by the LuzzyTool MCP server (luzzymeow/luzzytool). 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 →