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

27 lines
798 B
Markdown

# 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:
```bash
./jeannie prompt-injection-lab run
```
Useful commands:
```bash
./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.