AI agents call delete_skill to permanently remove resources in CodeForge MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion operations are inherently destructive and irreversible. Even without an explicit description, the 'delete_' prefix on a tool operating within a skill/capability management context indicates this tool permanently removes configuration or code artifacts. The high confidence is tempered slightly by the empty description, but the naming convention is a strong indicator of destructive intent.
From the tool's definition Tool name is 'delete_skill' which indicates irreversible deletion. The description is empty, but the verb 'delete' combined with the context of a skill management system on a code execution server strongly suggests permanent removal of data that cannot be…
Documented attack patterns abuse exactly the kind of access delete_skill gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeForge MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_skill:
{
"version": "1",
"default": "deny",
"hide": [
"delete_skill"
]
}delete_skill disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
delete_skill. It is categorised as a Destructive tool in the CodeForge MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CodeForge MCP server in PolicyLayer and add a rule for 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 CodeForge MCP. Nothing to install.
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 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 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.
delete_skill is provided by the CodeForge MCP server (max-rousseau/codeforge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeForge MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 CodeForge MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.