Delete ~/.config/shipeasy/config.json. No network call.
AI agents call auth_logout to permanently remove resources in Shipeasy — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes a local configuration file without network verification or reversibility. Although the blast radius is somewhat constrained (only affects the local shipeasy config), the action is destructive and cannot be undone. An AI agent invoking this during a logout attempt—or inadvertently—would cause loss of stored authentication credentials and configuration state.
From the tool's definition Tool description explicitly states 'Delete ~/.config/shipeasy/config.json' — irreversible deletion of a configuration file.
Attacks that exploit this kind of access
Delete ~/.config/shipeasy/config.json. No network call. It is categorised as a Destructive tool in the Shipeasy MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Shipeasy MCP server in PolicyLayer and add a rule for auth_logout: 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 Shipeasy. Nothing to install.
auth_logout 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 auth_logout 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 auth_logout. 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.
auth_logout is provided by the Shipeasy MCP server (shipeasy-ai/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 →