AI agents use layouts_push to create or update resources in Voog — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Voog environment.
This tool creates or updates Liquid templates in the CMS, which are reversible modifications (Write category). Severity is high because templates control site rendering and layout; misuse could deface or alter the appearance of the entire website. Confidence is high given the explicit 'PUT' operation described, though the description is terse.
From the tool's definition The tool performs PUT operations on .tpl (Liquid template) files, which modifies content in the Voog CMS. The verb 'push' combined with 'PUT' indicates creating or updating template files. Description states 'PUT each' file from a directory.
Attacks that exploit this kind of access
Read manifest.json + .tpl files from target_dir and PUT each. It is categorised as a Write tool in the Voog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Voog MCP server in PolicyLayer and add a rule for layouts_push: 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 Voog. Nothing to install.
layouts_push 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 layouts_push 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 layouts_push. 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.
layouts_push is provided by the Voog MCP server (runnel/voog-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 →