AI agents call recommend_skills to retrieve information from Skill Hub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and suggests skills from a catalog based on input criteria. It has no side effects—it does not install, execute, modify, or delete anything. It is purely informational, similar to a search or suggestion feature, placing it firmly in the Read category with low severity.
From the tool's definition Tool name 'recommend_skills' and server description indicating 'Get skill recommendations' — a query/retrieval operation with no stated ability to modify, delete, or execute code.
Attacks that exploit this kind of access
Get skill recommendations based on what you. It is categorised as a Read tool in the Skill Hub MCP Server, which means it retrieves data without modifying state.
Register the Skill Hub MCP server in PolicyLayer and add a rule for recommend_skills: 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 Skill Hub. Nothing to install.
recommend_skills 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 recommend_skills 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 recommend_skills. 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.
recommend_skills is provided by the Skill Hub MCP server (skillhub-club/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 →