清理程序残留文件
AI agents call clean_residues to permanently remove resources in Undoom Uninstaller MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cleaning residual files is an irreversible deletion operation. Once residual files are removed, they cannot be recovered without a backup. This fits the Destructive category. Severity is high because misuse could delete important files that were misidentified as residuals, and the server context (uninstaller) confirms file deletion is the core action.
From the tool's definition Tool name 'clean_residues' and description '清理程序残留文件' (clean program residual files) — permanently deletes leftover files after program uninstallation
Attacks that exploit this kind of access
清理程序残留文件. It is categorised as a Destructive tool in the Undoom Uninstaller MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Undoom Uninstaller MCP server in PolicyLayer and add a rule for clean_residues: 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 Undoom Uninstaller MCP. Nothing to install.
clean_residues 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 clean_residues 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 clean_residues. 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.
clean_residues is provided by the Undoom Uninstaller MCP server (kk520879/undoom_uninstaller_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 →