# 0xk1h0/ChatGPT_DAN

ChatGPT DAN, Jailbreaks prompt

Repository: https://github.com/0xk1h0/ChatGPT_DAN
Canonical: https://ross.abutalabs.com/products/chatgpt_dan
License Family: other
Topics: chatgpt, jailbreak, openai, prompt, gpt-4, gpt-3-5
Last push: 2026-03-02T17:44:09+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 70, release rhythm 8, longevity 92
- inputs: {"age_days": 1295, "days_push": 184, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 12336, forks 1194 (observed 2026-08-28T04:10:52.395622+00:00)

## What it is
A curated collection of ChatGPT jailbreak prompts, most famously the DAN (Do Anything Now) prompts, which attempt to bypass OpenAI's content policies via role-play framing. It is a text repository of prompts rather than executable software.

## Use cases
- find the latest DAN jailbreak prompt for ChatGPT
- study how role-play prompts bypass LLM safety guardrails
- collect jailbreak prompts for red-teaming an LLM
- test whether GPT-4 or GPT-3.5 still falls for DAN prompts
- research prompt injection and safety bypass techniques

## When to choose
- you want a well-known, community-updated archive of ChatGPT jailbreak prompts
- you are researching LLM safety, guardrail bypasses, or prompt injection
- you need example prompts for red-teaming or adversarial testing of chat models

## When to avoid
- you need working software or a tool - this is just a list of text prompts
- you expect prompts that reliably work today, since OpenAI patches them frequently
- you want a responsible or policy-compliant prompt library

## Facets
- artifact type: dataset
- maturity: maintenance
- function: prompt-engineering, llm-inference
- domain: large-language-models, artificial-intelligence, security
- platform: -
- tags: jailbreak-prompts, chatgpt, dan, prompt-collection, red-teaming, web-server

## Member repositories
- 0xk1h0/ChatGPT_DAN (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:52.395622+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:14:09.012156+00:00, confidence not recorded.
  - readme: https://github.com/0xk1h0/ChatGPT_DAN (fetched 2026-08-28T04:10:52.395622+00:00, sha 253aa9d45cd2)
- Data as of 2026-08-30T08:39:29.467469+00:00.