Change password for a cPanel account
AI agents use whm_change_password to create or update resources in ItchWHMMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ItchWHMMCP environment.
This tool changes the password of a cPanel account, which is a write operation (credential modification). It is reversible in the sense that the password can be changed again, but misuse could lock out legitimate users or enable unauthorized access. The blast radius is high because compromised credentials can lead to full account takeover.
From the tool's definition 'Change password for a cPanel account' — modifies credentials for an existing account
Attacks that exploit this kind of access
Change password for a cPanel account. It is categorised as a Write tool in the ItchWHMMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ItchWHM MCP server in PolicyLayer and add a rule for whm_change_password: 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 ItchWHMMCP. Nothing to install.
whm_change_password is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the whm_change_password 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 whm_change_password. 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.
whm_change_password is provided by the ItchWHM MCP server (manofsadness/itchwhmmcp). 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 →