Remove a local runner sandbox profile.
AI agents call remove_runner_sandbox_profile to permanently remove resources in Todos — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a sandbox profile is an irreversible operation that deletes configuration data and could disable security isolation for task runners. This prevents execution of tasks in isolated environments and cannot be easily undone. While not as critical as removing all tasks, it represents a destructive action on security infrastructure.
From the tool's definition Tool name 'remove_runner_sandbox_profile' indicates deletion/removal of a sandbox profile configuration. The verb 'remove' combined with deletion of security-relevant infrastructure (sandbox profiles) constitutes irreversible data destruction.
Attacks that exploit this kind of access
Remove a local runner sandbox profile. It is categorised as a Destructive tool in the Todos MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Todos MCP server in PolicyLayer and add a rule for remove_runner_sandbox_profile: 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 Todos. Nothing to install.
remove_runner_sandbox_profile is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_runner_sandbox_profile 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 remove_runner_sandbox_profile. 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.
remove_runner_sandbox_profile is provided by the Todos MCP server (@hasna/todos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →