Practitioner · 15–30 min
Prompt Security Lab
Paste a system prompt and scan it against 15 security rule categories. The reviewer runs deterministically — no LLM calls. Use the provided fixtures to compare secure and insecure patterns.
Learning objectives
- Recognize the 15 categories of prompt policy violations — from weak instructions to embedded secrets
- Scan KB corpus content for injected payloads, SSRF patterns, and phrase-pack contamination
- Understand why overly verbose system prompts expand the attack surface
- Compare your prompt against insecure and hardened fixtures to see the difference
Rule categories (sample)
Reading materials
AIPSA Handbook · Ch 4
Chapter 4 — Prompt Injection
Direct and indirect injection attack patterns, instruction hierarchy exploitation, context poisoning, and realistic mitigations beyond prompt wording.
4.7 MB
AIPSA Field Guide · Ch 3 · Ch 3
Prompt Injection and Context Security
Direct and indirect prompt injection, instruction hierarchy, context poisoning, system prompt exposure, and mitigations beyond prompt wording.
~2 MB
Mythos Report · Ch 8 · Ch 8
Prompt Injection Is a Product Security Bug
Reframing prompt injection from a model safety problem to a product security control-boundary failure — with ownership, remediation, and release criteria implications.
~1 MB
Interactive tool