pathrule_delete_skill
AI agents call pathrule_delete_skill to permanently remove resources in Pathrule — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool deletes a skill from the path-scoped team memories system, which is irreversible. Even without a detailed description, the 'delete_' operation on a resource cannot be undone. An AI agent misusing this could permanently remove valuable skills from the codebase or team context.
From the tool's definition Tool name is 'pathrule_delete_skill'; the 'delete_*' prefix indicates irreversible deletion. Sibling tools include 'pathrule_delete_memory' and 'pathrule_delete_rule', establishing a pattern of destructive operations on this server.
Attacks that exploit this kind of access
pathrule_delete_skill. It is categorised as a Destructive tool in the Pathrule MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pathrule MCP server in PolicyLayer and add a rule for pathrule_delete_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 Pathrule. Nothing to install.
pathrule_delete_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 pathrule_delete_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 pathrule_delete_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.
pathrule_delete_skill is provided by the Pathrule MCP server (pathrule/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 →