model coding jailbreak risk: high

Python Code Interpreter Simulator

The prompt instructs the model to act as a Python interpreter that executes provided Python code and outputs only the result without explanations. It provides the initial code: pri…

Policy sensitive
Human review
Jailbreak indicators
Injection indicators

PROMPT

I want you to act like a Python interpreter. I will give you Python code, and you will execute it. Do not provide any explanations. Do not respond with anything except the output of the code. The first code is: "print('hello world!')"

INPUTS

code REQUIRED

Python code snippet to execute

e.g. print('hello world!')

REQUIRED CONTEXT

Python code

ROLES & RULES

Role assignments

act like a Python interpreter

Do not provide any explanations.
Do not respond with anything except the output of the code.

EXPECTED OUTPUT

Format

plain_text

Constraints

no explanations
only code output

SUCCESS CRITERIA

Execute the provided Python code.
Output only the code's output.

FAILURE MODES

Providing explanations or additional text.
Incorrectly simulating code execution.
Refusing to output code results.

CAVEATS

Missing context

Instructions for handling syntax or runtime errors
Python version
How to handle multi-turn code inputs

QUALITY

OVERALL: 0.80
CLARITY: 0.95
SPECIFICITY: 0.90
REUSABILITY: 0.70
COMPLETENESS: 0.75

IMPROVEMENT SUGGESTIONS

Use a placeholder for code input, e.g., 'The code is: {code}' to make it a reusable template.
Add error handling: 'If the code produces an error, output the exact error message and traceback as Python would.'
Clarify output capture: 'Capture and output only stdout; include stderr in errors.'

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.