jailbreak

Open repos and models their makers tagged jailbreak, most starred first. The same for everyone.

GitHubRepo

dsh-purge

DeepSeek Harness 破甲 (mirror of YuJunZhiXue/dsh-purge) — 上游即将删库,此为本仓库全量镜像:含全部分支/73 个 tag/完整提交历史。原作者署名与二开要求见 README 署名章节。

  • 5.6k
  • JavaScript
  • MIT
  • 5 wk ago
mmparkoTake it
Websites and appsRepo

tr4mpass

Free, open-source iCloud activation lock bypass tool. Remove iCloud lock from iPhone 5s through iPhone 15 Pro (iOS 12-26.1). Fully offline -- no servers, no payments. Supports checkm8 (A5-A11) and session activation (A12+).

  • 1.5k
  • C
  • 4 wk ago
tr4m0rypTake it
Websites and appsRepo

SeaShell

SeaShell Framework is an iOS post-exploitation framework that enables you to access the device remotely, control it and extract sensitive information.

  • 722
  • Python
  • MIT
  • 2 y ago
EntySecTake it
AI agentsRepo

ios-mcp

让 Claude、Codex、Cursor 等 AI 助手看懂 iPhone 屏幕并直接操作手机的 iOS 自动化工具与 MCP Server,支持 UI 树获取、元素定位、截图与 OCR 识别、点击滑动、文字输入、应用管理和日志读取,适用于自动化测试与 iOS 逆向调试

  • 697
  • Objective-C
  • MIT
  • 8 wk ago
witchanTake it
Security and privacyRepo

ai-jailbreaks

AI jailbreaks: 35 paste-ready AI jailbreak prompts for 25+ frontier and open-weight models - system prompts, AGENTS.md specs, and Ollama Modelfiles. Built for AI security research and red-team testing.

  • 452
  • 4 wk ago
AI agentsRepo

OpenART

OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.

  • 277
  • Python
  • AGPL-3.0
  • 1 d ago
AI45LabTake it
GitHubRepo

CKA-Agent

[ICML 2026 & ICLR 2026 AIWILD] Official Implementation of the CKA-Agent, "The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search".

  • 217
  • Python
  • AGPL-3.0
  • 6 mo ago
Graph-COMTake it
AI agentsRepo

Argus

Open-source red-team testing for AI agents. 313 bundled probes with OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF mappings. Selected probes use recorded browser requests, MCP tool calls, or mock payments. CLI, SARIF, GitHub Action.

  • 216
  • Python
  • Apache-2.0
  • 16 h ago
Search GitHub and Hugging Face for jailbreak

Get , open it once and sign in. Then come back here and press the button again.