Load a skill to get specialized instructions. Call this when a skill listed in the system prompt matches the current task.
AI agents call load_skill to retrieve information from Ktx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves skill definitions to provide specialized instructions—this is a Read operation as it queries and returns data. However, confidence is medium rather than high because the description lacks specifics about whether loaded skills might trigger side effects or execute code. The 'medium' severity reflects that misuse could provide instructions for harmful actions, but the tool itself is read-only.
From the tool's definition Tool name 'load_skill' and description 'Load a skill to get specialized instructions' indicate retrieval of predefined skill definitions or instructions without modifying data.
Documented attack patterns abuse exactly the kind of access load_skill gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ktx, and nothing reaches the server without passing your rules. This is the rule we recommend for load_skill:
{
"version": "1",
"default": "deny",
"tools": {
"load_skill": {}
}
}load_skill 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.
Load a skill to get specialized instructions. Call this when a skill listed in the system prompt matches the current task. It is categorised as a Read tool in the Ktx MCP Server, which means it retrieves data without modifying state.
Register the Ktx MCP server in PolicyLayer and add a rule for load_skill: 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 Ktx. Nothing to install.
load_skill 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 load_skill 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 load_skill. 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.
load_skill is provided by the Ktx MCP server (kaelio/ktx). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ktx, 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.
10 Ktx tools catalogued and risk-classified — across an index of 43,000+ MCP servers.