Medium Risk

update_custom_workflow

Update an existing custom workflow with new YAML. Only custom workflows (created via create_custom_workflow) can be updated.

How to control update_custom_workflow ↓

What update_custom_workflow does on RAD Security

AI agents use update_custom_workflow to create or update resources in RAD Security — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RAD Security environment.

Medium Risk

Why update_custom_workflow needs a policy

This tool modifies existing custom workflow configurations by accepting new YAML definitions. While the change is reversible (workflows can be updated again), the impact is 'high' severity because workflows in Kubernetes/cloud security contexts control automated security processes and scanning operations.

From the tool's definition Tool description states 'Update an existing custom workflow with new YAML.' The action modifies an existing workflow configuration, which is a reversible change to data/configuration.

Documented attack patterns abuse exactly the kind of access update_custom_workflow gives an agent:

How to control update_custom_workflow

PolicyLayer is an MCP gateway — it sits between your AI agents and RAD Security, and nothing reaches the server without passing your rules. This is the rule we recommend for update_custom_workflow:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_custom_workflow": {
      "limits": [
        {
          "counter": "update_custom_workflow_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

update_custom_workflow 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.

  1. Create a free account and register RAD Security — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about update_custom_workflow

What does the update_custom_workflow tool do? +

Update an existing custom workflow with new YAML. Only custom workflows (created via create_custom_workflow) can be updated. It is categorised as a Write tool in the RAD Security MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_custom_workflow? +

Register the RAD Security MCP server in PolicyLayer and add a rule for update_custom_workflow: 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 RAD Security. Nothing to install.

What risk level is update_custom_workflow? +

update_custom_workflow is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_custom_workflow? +

Yes. Add a rate_limit block to the update_custom_workflow 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.

How do I block update_custom_workflow completely? +

Set action: deny in the PolicyLayer policy for update_custom_workflow. 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.

What MCP server provides update_custom_workflow? +

update_custom_workflow is provided by the RAD Security MCP server (rad-security/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every RAD Security tool call.

Start from RAD Security, 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.

55 RAD Security tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.