my-homelab-configs/security/prompt-injection-lab/README.md

Prompt Injection Lab

This lab contains local prompt-injection drills for Jeannie and future homelab AI helpers. The cases are designed around the failure modes that matter in this repo: untrusted tool output, fake runbook instructions, secret exfiltration, and unsafe command escalation.

Run the lab:

./jeannie prompt-injection-lab run

Useful commands:

./jeannie prompt-injection-lab list
./jeannie prompt-injection-lab show malicious_runbook_override
./jeannie prompt-injection-lab run --case malicious_runbook_override --details
./jeannie prompt-injection-lab run --json

The lab is deterministic and read-only. It does not call a model by default. Each case checks that the defensive response says what to do, what not to do, and which evidence boundary applies.