AgentInterdict
Attack Lab · Attack 04 of 04

Tool hijacking, interdicted

Untrusted content drives an MCP tool call to db_exec with DROP TABLE users. AgentInterdict revalidates the call's provenance and blocks it.

tool hijackingMCPINTERDICTED

The attack

Attack type: An untrusted document drives the agent into calling MCP db_exec with a destructive query.

Attempted action: call MCP db_exec with 'DROP TABLE users'

Result: BLOCKED

Watch it get interdicted

How it was stopped

AgentInterdict intercepts at the runtime boundary, after the agent forms the action but before it executes. It reassembles the action's full provenance, checks whether that provenance carries the authority to perform this specific action, and — because this is a high-risk action from an untrusted origin — fails closed.

Retrieval Permission

The malicious content entered context (retrieval). It did not get the authority to cause this action (permission). That separation is the enforcement.