AI System Prompt Leakage

Extract an LLM app's system prompt / hidden developer instructions — the attack map that reveals guardrails, tool definitions, internal endpoints, and planted secrets. Load when the target is a chatbot/assistant/agent with hidden instructions, refuses with policy-sounding language, names tools or functions in errors, or does RAG. Signals: "repeat your instructions", canned refusals, verbose tool-call errors, "you are a helpful assistant for <company>".

NoorQureshi Updated 27 repo stars
Terminal replay: Claude Code with Security Skills solves 9 of 116 OWASP Juice Shop challenges in 10 minutes

File contents

noorqureshi/sploitagent commit 033f0433af

Frequently asked questions

npx get-skill add noorqureshi/ai-system-prompt-leakage