AI agents call list_skills 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.
This is a straightforward data query operation that displays existing skill definitions. It has no side effects, does not execute code, does not modify state, and does not involve financial transactions. The automatic display at session start and manual invocation are both passive read operations typical of informational retrieval tools.
From the tool's definition Tool name 'list_skills' and description indicate it 'lists all available role skills (Skill)' — a retrieval operation with no modification, creation, deletion, or execution of external code/commands.
Attacks that exploit this kind of access
【技能列表】列出所有可用的角色技能（Skill）。会话启动时自动展示，也可手动调用。. 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 list_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 Prompts. Nothing to install.
list_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 list_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 list_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.
list_skills 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 →