delete_change_set
AI agents call delete_change_set to permanently remove resources in Sceptre — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although a change set represents a staged rather than deployed change, deleting it is irreversible and removes the ability to review or apply that infrastructure modification. This qualifies as Destructive rather than Write. The severity is high because unintended deletion could cause loss of important planned infrastructure changes and disrupt deployment workflows.
From the tool's definition Tool name is 'delete_change_set'; it is paired with 'create_change_set' on a CloudFormation management server. Deleting a change set removes a prepared but unapplied infrastructure change, which is irreversible.
Attacks that exploit this kind of access
delete_change_set. It is categorised as a Destructive tool in the Sceptre MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sceptre MCP server in PolicyLayer and add a rule for delete_change_set: 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 Sceptre. Nothing to install.
delete_change_set 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_change_set 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_change_set. 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_change_set is provided by the Sceptre MCP server (sceptre/sceptre-mcp-server). 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 →