Delete a user-installed skill (bundled skills cannot be removed).
AI agents call skill_uninstall to permanently remove resources in LocalAnt — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool removes installed skills from the system without possibility of automatic recovery through the tool itself. While the impact is scoped to user-installed skills only (not bundled ones), the action is irreversible and represents permanent removal of functionality or data. This qualifies as Destructive rather than Write, which is reserved for reversible modifications.
From the tool's definition Tool name 'skill_uninstall' combined with description 'Delete a user-installed skill' explicitly performs deletion. The word 'Delete' and 'uninstall' indicate irreversible removal of data/software artifacts.
Attacks that exploit this kind of access
Delete a user-installed skill (bundled skills cannot be removed). It is categorised as a Destructive tool in the LocalAnt MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the LocalAnt MCP server in PolicyLayer and add a rule for skill_uninstall: 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 LocalAnt. Nothing to install.
skill_uninstall 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 skill_uninstall 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 skill_uninstall. 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.
skill_uninstall is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →