Remove an added skill. Omit skill_name to remove all added skills.
AI agents call remove_skill to permanently remove resources in Zanat — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently deletes skills from the system. The ability to remove all skills at once with a single parameter omission amplifies the destructive impact. This is not reversible through standard update/write operations and represents data loss, making it Destructive rather than Write.
From the tool's definition 'Remove an added skill' with option to 'remove all added skills' - this is irreversible deletion of user-configured data without recovery mechanism mentioned.
Attacks that exploit this kind of access
Remove an added skill. Omit skill_name to remove all added skills. It is categorised as a Destructive tool in the Zanat MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Zanat MCP server in PolicyLayer and add a rule for remove_skill: 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 Zanat. Nothing to install.
remove_skill 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_skill 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_skill. 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_skill is provided by the Zanat MCP server (@iamramo/zanat-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 →