AI agents use add_consignment_attachments to create or update resources in Gobox — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gobox environment.
This tool modifies consignment records by attaching files, which is a reversible write operation. While it affects consignment data, it does not delete or destroy data (not Destructive), does not execute code or trigger external operations (not Execute), and does not move money (not Financial).
From the tool's definition The tool name 'add_consignment_attachments' and description 'Add attachment files to a consignment' indicate file attachment creation/modification. This is a write operation that creates new data (attachment records) associated with an existing consignment.
Attacks that exploit this kind of access
Add attachment files to a consignment. It is categorised as a Write tool in the Gobox MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gobox MCP server in PolicyLayer and add a rule for add_consignment_attachments: 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 Gobox. Nothing to install.
add_consignment_attachments 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 add_consignment_attachments 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 add_consignment_attachments. 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.
add_consignment_attachments is provided by the Gobox MCP server (winter279/gobox-mcp). 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 →