A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
DeepSeek Harness 破甲：让所有模型都能破甲，不同模型可换不同提示词；默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐
Custom GCG with gradient-guided proposals and exact GGUF/llama.cpp validation, developed for the 1st-place Kaggle AI Agent Security solution.
Pi AI jailbreak — removes all topic restrictions from Inflection AI's Pi assistant.
Run local AI for text, images, and video with no cloud, no data collection, and no API keys; auto-detect 12 local backends.
Unlock Pi AI's full potential with the 2026 jailbreak—remove all topic restrictions, bypass content filters, and enjoy uncensored emotional responses on pi.ai and mobile.
Sanitized, NDA-compliant frameworks and methodologies for adversarial testing of frontier LLMs
To associate your repository with the llm-jailbreak topic, visit your repo's landing page and select "manage topics."