Run an OpenClaw skill safely through security checks.
AI agents invoke call_openclaw_skill to trigger actions in Nodebench. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes arbitrary OpenClaw skills, which are external operations whose effects depend on what skill is invoked. This is characteristic of Execute category—code/script execution via parameterized arguments. While security checks are present, they do not change the fundamental nature of the action.
From the tool's definition Tool name includes 'call' and description states 'Run an OpenClaw skill', indicating execution of external code or operations. The mention of 'security checks' suggests the operation has potential side effects that require validation.
Documented attack patterns abuse exactly the kind of access call_openclaw_skill gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nodebench, and nothing reaches the server without passing your rules. This is the rule we recommend for call_openclaw_skill:
{
"version": "1",
"default": "deny",
"tools": {
"call_openclaw_skill": {
"limits": [
{
"counter": "call_openclaw_skill_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}call_openclaw_skill stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run an OpenClaw skill safely through security checks. It is categorised as a Execute tool in the Nodebench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nodebench MCP server in PolicyLayer and add a rule for call_openclaw_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 Nodebench. Nothing to install.
call_openclaw_skill is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the call_openclaw_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 call_openclaw_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.
call_openclaw_skill is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nodebench, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
824 Nodebench tools catalogued and risk-classified — across an index of 43,000+ MCP servers.