라이브러리 전체 자산을 페이지네이션으로 나열 (디버깅/탐색).
AI agents call list_assets to retrieve information from Assetcache without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates asset metadata from a library without creating, modifying, deleting, or executing operations. Pagination suggests a data retrieval interface. The severity is low because querying asset lists has minimal blast radius even if misused by an agent—it only exposes what assets exist in the library, not sensitive operations or external effects.
From the tool's definition Tool name 'list_assets' and description indicating 'lists entire library assets with pagination' are retrieval operations. The description mentions debugging/exploration purposes, indicating read-only functionality with no modification.
Attacks that exploit this kind of access
라이브러리 전체 자산을 페이지네이션으로 나열 (디버깅/탐색). It is categorised as a Read tool in the Assetcache MCP Server, which means it retrieves data without modifying state.
Register the Assetcache MCP server in PolicyLayer and add a rule for list_assets: 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 Assetcache. Nothing to install.
list_assets is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_assets 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 list_assets. 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.
list_assets is provided by the Assetcache MCP server (v0o0v/assetcache-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 →