Permanently delete all files in Trash.
AI agents call empty_trash to permanently remove resources in Yadisk — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes all files in the trash without recovery options. Although the blast radius is confined to files already in trash (not live data), the permanence and bulk nature of the operation justify 'Destructive' category and 'high' severity. An AI misusing this could cause unintended data loss if the user had files in trash they wanted to recover.
From the tool's definition Tool name 'empty_trash' combined with description 'Permanently delete all files in Trash' indicates irreversible deletion of data. The word 'Permanently' explicitly signals the destructive nature of this operation.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Permanently delete all files in Trash. It is categorised as a Destructive tool in the Yadisk MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Yadisk MCP server in PolicyLayer and add a rule for empty_trash: 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 Yadisk. Nothing to install.
empty_trash 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 empty_trash 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 empty_trash. 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.
empty_trash is provided by the Yadisk MCP server (patr56/yadisk-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 →