AI agents call select_skill to retrieve information from Prompts without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool selects and retrieves a Skill, returning its full prompt content. This is a read/query operation that fetches existing data without modifying or creating anything. No side effects are described.
From the tool's definition 选择一个 Skill 作为当前身份角色。返回该 Skill 的完整 prompt（身份 + 开发规范 + 学习记录）
Attacks that exploit this kind of access
【选择技能】选择一个 Skill 作为当前身份角色。返回该 Skill 的完整 prompt（身份 + 开发规范 + 学习记录）。会话开始时应询问用户选择哪个 Skill。. It is categorised as a Read tool in the Prompts MCP Server, which means it retrieves data without modifying state.
Register the Prompts MCP server in PolicyLayer and add a rule for select_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 Prompts. Nothing to install.
select_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 select_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 select_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.
select_skill is provided by the Prompts MCP server (thana0623/pmcp-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 →