Delete a file by ID.
AI agents call delete_file to permanently remove resources in Smokeball — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes files from the law firm's practice management system. In a legal context, file deletion is irreversible and can result in loss of critical case documents, evidence, or client records. While not financial in nature, the destructive impact on data integrity and potential compliance/discovery violations makes this a high-severity Destructive action.
From the tool's definition The tool is named 'delete_file' with description 'Delete a file by ID.' The word 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a file by ID. It is categorised as a Destructive tool in the Smokeball MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Smokeball MCP server in PolicyLayer and add a rule for delete_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 Smokeball. Nothing to install.
delete_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_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_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_file is provided by the Smokeball MCP server (rosenadvertising/smokeball-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 →