update_skill · Prompts MCP: Risk & Policy

WHAT IT DOES

What update_skill does on Prompts

AI agents use update_skill to create or update resources in Prompts — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Prompts environment.

WHY IT NEEDS A POLICY

Why update_skill needs a policy

update_skill creates or modifies persistent skill records and learning metadata within the prompts system. While the modifications are reversible (Write rather than Destructive), this represents data mutation with blast radius: incorrect skill updates could degrade AI assistant behavior in future sessions, leading to compounded errors.

From the tool's definition Tool description states 'update' and 'modify' actions ('修改开发规范' = modify development standards, '更新描述' = update descriptions) on skill records and learning logs. These are reversible data modifications.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_skill Rate-limited

update_skill stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_skill": {
      "limits": [
        {
          "counter": "update_skill_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Prompts, so you can run agents against it safely.

FAQ

Questions about update_skill

What does the update_skill tool do? +

【技能自优化】会话结束时调用，总结本次开发经验并更新 Skill。可追加学习记录、修改开发规范、更新描述。智能体应主动在每次开发后调用此工具自我进化。. It is categorised as a Write tool in the Prompts MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_skill? +

Register the Prompts MCP server in PolicyLayer and add a rule for update_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.

What risk level is update_skill? +

update_skill is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_skill? +

Yes. Add a rate_limit block to the update_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.

How do I block update_skill completely? +

Set action: deny in the PolicyLayer policy for update_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.

What MCP server provides update_skill? +

update_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.