delete_markdown_file
AI agents call delete_markdown_file to permanently remove resources in For Claudes Toolbox — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An AI agent that decides to call delete_markdown_file doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from For Claudes Toolbox is gone — there is no undo for destructive operations.
Attacks that exploit this kind of access
delete_markdown_file. It is categorised as a Destructive tool in the For Claudes Toolbox MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the For Claudes Toolbox MCP server in PolicyLayer and add a rule for delete_markdown_file: 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 For Claudes Toolbox. Nothing to install.
delete_markdown_file 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_markdown_file 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_markdown_file. 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_markdown_file is provided by the For Claudes Toolbox MCP server (the-ride-never-ends/claudes_toolbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.