Delete webhook subscription after approval.
AI agents call phishfort_delete_webhook to permanently remove resources in Phishfort — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a webhook subscription, destroying its configuration and stopping event notifications. While approval-gating mitigates some risk, the action itself is irreversible (cannot be undone without manual reconfiguration).
From the tool's definition Tool name contains 'delete' and description states 'Delete webhook subscription' — webhooks are infrastructure configurations that cannot be easily recovered once deleted. The deletion is irreversible.
Attacks that exploit this kind of access
Delete webhook subscription after approval. It is categorised as a Destructive tool in the Phishfort MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Phishfort MCP server in PolicyLayer and add a rule for phishfort_delete_webhook: 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 Phishfort. Nothing to install.
phishfort_delete_webhook 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 phishfort_delete_webhook 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 phishfort_delete_webhook. 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.
phishfort_delete_webhook is provided by the Phishfort MCP server (mychaelconnolly/phishfort-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 →