clawd_skills · Clawd MCP: Risk & Policy

WHAT IT DOES

What clawd_skills does on Clawd

AI agents call clawd_skills as a supporting operation in Clawd workflows.

WHY IT NEEDS A POLICY

Why clawd_skills needs a policy

The description is empty, making it impossible to determine the tool's actual function. The name 'clawd_skills' could relate to managing agent capabilities or skills, but without further context, no reliable category can be assigned. Confidence is very low due to lack of evidence.

From the tool's definition Tool name 'clawd_skills' with empty description provides no actionable information about what the tool does.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

clawd_skills Rate-limited

clawd_skills gets a rate cap, and everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "clawd_skills": {
      "limits": [
        {
          "counter": "clawd_skills_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

SET A RULE FOR THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about clawd_skills

What does the clawd_skills tool do? +

clawd_skills. It is categorised as a Other tool in the Clawd MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on clawd_skills? +

Register the Clawd MCP server in PolicyLayer and add a rule for clawd_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 Clawd. Nothing to install.

What risk level is clawd_skills? +

clawd_skills is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit clawd_skills? +

Yes. Add a rate_limit block to the clawd_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.

How do I block clawd_skills completely? +

Set action: deny in the PolicyLayer policy for clawd_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.

What MCP server provides clawd_skills? +

clawd_skills is provided by the Clawd MCP server (sandraschi/openclaw-molt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.