skill_generate_from_prompt · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What skill_generate_from_prompt does on LocalAnt

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

WHY IT NEEDS A POLICY

Why skill_generate_from_prompt needs a policy

This tool generates and persists code artifacts (skill skeletons) as output. While the skill is created in a disabled state (mitigating immediate execution risk), the act of saving a new skill is a Write operation—it creates reversible, structured data that can be modified or deleted. It does not execute code directly (hence not Execute) and does not destroy data (not Destructive).

From the tool's definition Tool creates/generates a new skill skeleton that is saved (reversible write operation). Description explicitly states the output is 'saved DISABLED with declared permissions', indicating creation of persistent data/code artifact.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

skill_generate_from_prompt Rate-limited

skill_generate_from_prompt 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": {
    "skill_generate_from_prompt": {
      "limits": [
        {
          "counter": "skill_generate_from_prompt_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 LocalAnt, so you can run agents against it safely.

FAQ

Questions about skill_generate_from_prompt

What does the skill_generate_from_prompt tool do? +

Generate a new skill skeleton from a natural-language spec. The skill is saved DISABLED with declared permissions; review and validate before enabling. It is categorised as a Write tool in the LocalAnt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on skill_generate_from_prompt? +

Register the LocalAnt MCP server in PolicyLayer and add a rule for skill_generate_from_prompt: 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 LocalAnt. Nothing to install.

What risk level is skill_generate_from_prompt? +

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

Can I rate-limit skill_generate_from_prompt? +

Yes. Add a rate_limit block to the skill_generate_from_prompt 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 skill_generate_from_prompt completely? +

Set action: deny in the PolicyLayer policy for skill_generate_from_prompt. 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 skill_generate_from_prompt? +

skill_generate_from_prompt is provided by the LocalAnt MCP server (yuga-hashimoto/localant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.