Create or delete the Sandy sandbox image
AI agents call sandy_image to permanently remove resources in Sandy — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
While image creation is a Write operation, the tool's ability to delete the sandbox image makes this Destructive. Deletion of infrastructure components is irreversible and prevents further use of that image, fitting the Destructive category. In a sandboxed environment context, destroying the image could disrupt AI agent operations and require recreation.
From the tool's definition The tool description explicitly states it can 'delete the Sandy sandbox image', which is an irreversible operation that destroys infrastructure/resources.
Attacks that exploit this kind of access
Create or delete the Sandy sandbox image. It is categorised as a Destructive tool in the Sandy MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sandy MCP server in PolicyLayer and add a rule for sandy_image: 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 Sandy. Nothing to install.
sandy_image 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 sandy_image 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 sandy_image. 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.
sandy_image is provided by the Sandy MCP server (jamestelfer/sandy). 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 →