AI agents call skill_list_assets to retrieve information from ClaudeSkills MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to list or enumerate existing assets within the skill system. Listing is a non-destructive, read-only operation with no side effects. The low severity reflects that listing assets poses minimal risk—the worst case would be information disclosure of asset names or metadata, which is low-impact.
From the tool's definition Tool name 'skill_list_assets' indicates listing/enumeration of assets. Sibling tools include 'skill_read_asset' and 'skill_search_index', which are clearly Read operations.
Documented attack patterns abuse exactly the kind of access skill_list_assets gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ClaudeSkills MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for skill_list_assets:
{
"version": "1",
"default": "deny",
"tools": {
"skill_list_assets": {}
}
}skill_list_assets is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
skill_list_assets. It is categorised as a Read tool in the ClaudeSkills MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ClaudeSkills MCP Server MCP server in PolicyLayer and add a rule for skill_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 ClaudeSkills MCP Server. Nothing to install.
skill_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 skill_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 skill_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.
skill_list_assets is provided by the ClaudeSkills MCP Server MCP server (tsoernes/skills-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ClaudeSkills MCP Server, 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.
13 ClaudeSkills MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.