AI agents call search_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 is a query/search operation that retrieves information about available skills from a catalog. It has no side effects—it only reads and returns data matching search criteria. No code execution, data modification, deletion, or financial transactions are involved. The low severity reflects minimal risk from misuse.
From the tool's definition Tool performs 'search' using 'semantic matching' to return skills; no modification, deletion, execution, or financial operations occur.
Attacks that exploit this kind of access
Search for Claude Code Skills using natural language. Returns relevant skills based on semantic matching. 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 search_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.
search_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 search_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 search_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.
search_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 →