[ACTION] Build a package-removal command — never auto-executed.
AI agents call remove_packages to permanently remove resources in Cachyos — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool removes packages from the system, which cannot be automatically undone. Even though the description states it 'never auto-executed' (meaning the command is built but not run automatically), the tool's core function is to facilitate package deletion. Package removal is irreversible unless manually reinstalled, making this a Destructive action.
From the tool's definition Tool name contains 'remove_packages' and description indicates '[ACTION] Build a package-removal command'. Package removal is irreversible without manual reinstallation and constitutes destructive data loss.
Attacks that exploit this kind of access
[ACTION] Build a package-removal command — never auto-executed. It is categorised as a Destructive tool in the Cachyos MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Cachyos MCP server in PolicyLayer and add a rule for remove_packages: 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 Cachyos. Nothing to install.
remove_packages 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 remove_packages 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 remove_packages. 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.
remove_packages is provided by the Cachyos MCP server (raindancer118/cachyos-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 →