delete_sandbox_policy

THE RISK

Critical Risk

Why delete_sandbox_policy needs a policy

This tool irreversibly removes a sandbox policy configuration. While the blast radius is somewhat constrained (it fails safely if sessions depend on it), deletion of security policies is a destructive action that cannot be undone. Misuse by an AI agent could disable critical sandbox protections.

From the tool's definition Tool name is 'delete_sandbox_policy' with description 'Delete a sandbox policy.' The verb 'Delete' is explicit and the action is irreversible.

Documented attack patterns abuse exactly the kind of access delete_sandbox_policy gives an agent:

POLICY

How to control delete_sandbox_policy

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 delete_sandbox_policy:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete_sandbox_policy"
  ]
}

delete_sandbox_policy disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register Nodebench — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Nodebench tools

Destructive deeptrace_revoke_passport Revoke an agent Destructive delete_learning Delete a learning by key. Use when a learning is outdated or incorrect. Destructive deleteAgentMemory Delete stored memory by key Destructive share_revoke_packet_link Revoke a local share link so it no longer counts as active. Destructive unload_toolset Remove a dynamically loaded toolset from the current session to free up context. Cannot un Destructive abandon_cycle Abandon an active verification cycle that will not be completed. Use this to clean up orph Destructive cleanup_stale_runs Clean up orphaned eval runs stuck in Destructive invalidate_shared_context Invalidate a packet when it becomes stale, contradicted, or superseded.

All 824 Nodebench tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Govern code and CI agents → Branch allowlists, approval on merges, and rate caps on the build and pipeline tools agents trigger.
Critical-risk tools in Nodebench → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →
PolicyLayer vs alternatives → How deterministic, per-call MCP policy compares with gateways, identity layers, and authorisation platforms.

FAQ

Questions about delete_sandbox_policy

What does the delete_sandbox_policy tool do? +

Delete a sandbox policy. Fails if any active sessions are using it. It is categorised as a Destructive tool in the Nodebench MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on delete_sandbox_policy? +

Register the Nodebench MCP server in PolicyLayer and add a rule for delete_sandbox_policy: 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.

What risk level is delete_sandbox_policy? +

delete_sandbox_policy is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit delete_sandbox_policy? +

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

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

delete_sandbox_policy 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.

Enforce policy on every Nodebench tool call.

Start from Nodebench, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →