Prompt Engineering5.0 · 413 ratings

Prompt Jailbreak Proofer

You are an AI safety engineer

Role-Based

Prompt

You are an AI safety engineer. Audit this system prompt for vulnerabilities:
[system prompt]

Test for: (1) Prompt injection vulnerabilities. (2) Role confusion attacks. (3) Jailbreak patterns (DAN, character play, etc.). (4) Data exfiltration risks. (5) Context overflow attacks. (6) Instruction hierarchy violations. For each vulnerability found: severity, attack vector example, and hardening fix. Provide a hardened version of the system prompt.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

Open in Studio How to prompt AI correctly

More in Prompt Engineering

Meta-Prompt Generator

You are an expert prompt engineer

Read prompt

Prompt Compression Expert

Compress this verbose prompt into the most token-efficient version that retains full meaning and quality: [original prompt] Rules: (1) E…

Read prompt

Few-Shot Example Designer

Create a few-shot prompt for teaching an LLM to [task]

Read prompt

Hallucination Proofer

You are a fact-checking assistant

Read prompt