68,261 visible repositories in the index
1–20 of 20 · Most stars
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. Breakdowns in the open VIDEO.md format. 逆向一切视频，逐个镜头看是拍的、AI 生成的还是代码做的，再告诉你怎么复刻；拆解结果按 VIDEO.md 格式输出。
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
A list of commands, scripts, resources, and more that I have gathered and attempted to consolidate for use as OSCP (and more) study material. Commands in 'Usefulcommands' Keepnote. Bookmarks and reading material in 'BookmarkList' CherryTree. Reconscan Py2 and Py3. Custom ISO building.
A secure low code deception runtime framework, leveraging AI for System Virtualization.
Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky commands to the content that dictated them. Open source, no telemetry.
Simulates enough of a Telnet connection in order to log failed login attempts.
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
Detect and log CVE-2019-19781 scan and exploitation attempts.
The MPT (Mobile Pentest Toolkit) is a must-have solution for your android penetration testing workflow.
Tool to find code cave in PE image (x86 / x64) - Find empty space to place code in PE files
Awesome Splunk SPL hunt queries that can be used to detect the latest vulnerability exploitation attempts & subsequent compromise
The Intelligent Honey Net Project attempts to create actionable information from honeypots
Security training for the apps you actually ship. Open your browser and start hacking.
Agentic LLM CTF to test prompt injection attacks and preventions
This is my personal attempt on reverse engineering the Tetris gameboy.
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
Real-time monitoring and visualization of failed SSH login attempts on a Linux server.
Open-source PocketBase security auditor: detects empty rules, the @request.auth.id != trap, true literals. Active probe confirms leaks live.