AI agents use update_agent to create or update resources in Apple Shortcuts — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Apple Shortcuts environment.
The tool updates an existing agent, which is a reversible modification operation. This falls under Write rather than Execute because the action itself is data modification, not execution of arbitrary code or commands. Severity is medium because updating agents could affect automation/workflow behavior, but the operation is reversible and the blast radius depends on what agent properties can be modified.
From the tool's definition Tool name is 'update_agent' and description states 'Update an existing agent', which modifies existing data.
Documented attack patterns abuse exactly the kind of access update_agent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Apple Shortcuts, and nothing reaches the server without passing your rules. This is the rule we recommend for update_agent:
{
"version": "1",
"default": "deny",
"tools": {
"update_agent": {
"limits": [
{
"counter": "update_agent_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_agent stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update an existing agent. It is categorised as a Write tool in the Apple Shortcuts MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Apple Shortcuts MCP server in PolicyLayer and add a rule for update_agent: 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 Apple Shortcuts. Nothing to install.
update_agent 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 update_agent 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 update_agent. 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.
update_agent is provided by the Apple Shortcuts MCP server (@mindstone/mcp-server-apple-shortcuts). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Apple Shortcuts, 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.
423 Apple Shortcuts tools catalogued and risk-classified — across an index of 43,000+ MCP servers.