ShadowHackrs/Jailbreaks-GPT-Gemini-deepseek- resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1197 stars · 209 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A curated collection of jailbreak prompts targeting GPT, Sora, Claude, Gemini, and DeepSeek, claimed to bypass model safety restrictions. It is presented as educational/research material for studying LLM guardrails and prompt injection techniques.

Use cases

• study how LLM safety guardrails can be bypassed
• red-team testing of chatbot content filters
• research prompt injection techniques against GPT and Gemini
• collect examples of jailbreak prompts for security analysis
• learn about adversarial prompting against AI models

When to choose

• you are a security researcher analyzing LLM jailbreak techniques
• you need a reference corpus of adversarial prompts for red-teaming
• you want to study how model guardrails are circumvented

When to avoid

• you want to actually bypass AI provider terms of service
• you need production-ready or maintained software - this is just a prompt list
• you require a permissively licensed project - no license is provided

Facets

dataset · maturity active

prompt-engineering security large-language-models security artificial-intelligence cross-platform jailbreak-prompts llm-safety-research prompt-collection red-teaming

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ShadowHackrs/Jailbreaks-GPT-Gemini-deepseek-")