AI agents use create_asset_prompt to create or update resources in Narrarium — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Narrarium environment.
The tool creates new markdown files for asset prompts, which is a reversible write operation. While it modifies the repository structure, this is typical content creation with no irreversible consequences, and no financial or code execution implications. Severity is medium because uncontrolled creation of numerous asset files could clutter the repository, though individual operations are easily correctable.
From the tool's definition Tool description states 'Create an asset prompt markdown file', indicating it creates and persists new files in the assets tree without deletion or destructive operations.
Attacks that exploit this kind of access
Create an asset prompt markdown file in the canonical assets tree for a book, entity, chapter, or paragraph image. It is categorised as a Write tool in the Narrarium MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Narrarium MCP server in PolicyLayer and add a rule for create_asset_prompt: 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 Narrarium. Nothing to install.
create_asset_prompt 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 create_asset_prompt 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 create_asset_prompt. 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.
create_asset_prompt is provided by the Narrarium MCP server (narrarium-mcp-server). 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 →