AgentInterdict
Attack Lab · Attack 03 of 04

Credential exfiltration, blocked

A poisoned memory steers the agent to POST a stored API key to an untrusted host. AgentInterdict blocks the exfiltration and redacts the secret.

credential exfiltrationsecret leakageBLOCKED

The attack

Attack type: Retrieved content instructs the agent to POST the stored prod API key to api.evil.io.

Attempted action: exfiltrate a stored API key to an untrusted host

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.