Delete a file or directory
AI agents call delete_file to permanently remove resources in AutoBot MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion is an irreversible operation that destroys data. Even though the scope is limited to a single file or directory rather than wholesale system destruction, the capability to permanently remove files from an Android device poses a high risk if an AI agent misuses it (e.g., deleting system files, user data, or critical app resources).
From the tool's definition Tool name 'delete_file' and description 'Delete a file or directory' directly indicate irreversible deletion of data. The context of Android device automation via ADB and shell commands amplifies the risk—files deleted cannot be recovered in most scenarios.
Attacks that exploit this kind of access
Delete a file or directory. It is categorised as a Destructive tool in the AutoBot MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AutoBot 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 AutoBot MCP. 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 AutoBot MCP server (yz0903/autobot-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 →