Manage sandbox containers for agent isolation
Part of the OpenClaw server.
Free to start. No card required.
AI agents use sandbox to create or modify resources in OpenClaw. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call sandbox repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach OpenClaw.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"sandbox": {
"limits": [
{
"counter": "sandbox_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full OpenClaw policy for all 129 tools.
These attack patterns abuse exactly the kind of access sandbox gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Manage sandbox containers for agent isolation. It is categorised as a Write tool in the OpenClaw MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OpenClaw MCP server in PolicyLayer and add a rule for sandbox: 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 OpenClaw. Nothing to install.
sandbox is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the sandbox 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 sandbox. 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.
sandbox is provided by the OpenClaw MCP server (openclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 129 OpenClaw tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.