AI agents use copy_files to create or update resources in LuzzyTool — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LuzzyTool environment.
This tool creates new copies of files in a target directory, which is a reversible write operation. It does not delete originals (unlike move), does not execute code, and does not destroy data. The severity is medium because uncontrolled batch copying could fill disk space, overwrite existing files, or expose sensitive data if copied to unintended locations.
From the tool's definition Tool name 'copy_files' and description '【批量复制】将多个源文件一次性复制到目标目录' (batch copy multiple source files to target directory at once) indicate file creation/duplication functionality.
Attacks that exploit this kind of access
【批量复制】将多个源文件一次性复制到目标目录。. It is categorised as a Write tool in the LuzzyTool MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LuzzyTool MCP server in PolicyLayer and add a rule for copy_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.
copy_files 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 copy_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 copy_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.
copy_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 →