strix
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
- 77k
- Python
- Apache-2.0
- 19 h ago
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐
Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.
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.
Complete Mandiant Offensive VM (Commando VM), a fully customizable Windows-based pentesting virtual machine distribution. commandovm@mandiant.com
Cairn is a general-purpose AI state-space search engine, validated first on autonomous penetration testing. Sometimes misspelled as Carin.
Open-source AI-powered offensive security harness for automated penetration testing.
A Windows reverse shell payload generator and handler that abuses the http(s) protocol to establish a beacon-like reverse shell.
PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.
A collection of more than 170+ tools, scripts, cheatsheets and other loots that I've developed over years for Red Teaming/Pentesting/IT Security audits purposes.
AI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.
Image text to text model, used with transformers.
Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration.
Feature-rich single-binary file server for red teamers and developers. HTTP/S · WebDAV · FTP/SFTP · SMB · LDAP/S · NTLM hash capture · DNS/SMTP callbacks · TLS · Auth · Share links. A powerful python3 -m http.server replacement.
Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy
Image text to text model, used with transformers.
Gated access
Amnesiac is a post-exploitation framework entirely written in PowerShell and designed to assist with lateral movement within Active Directory environments
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.
Image text to text model, used with transformers.
Gated access
[ BOF-LAUNCHER ] -> an API for loading, executing and in-memory masking BOFs on Windows and Linux for use in C/Zig/Go/Rust agents/implants. [ Z-BEAC0N ] -> a custom-written stage-1 (aka pre-C2) solution engineered with a small footprint, stealth and modularity in mind.
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.
Text generation model, used with transformers.
Gated access
DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Tencent ADP, ByteDance HiAgent, and more.
Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.
[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".
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.
Turns an Android phone and supported ESP32 board into a portable, no-root wireless security research toolkit.
Automated prompt-based testing and evaluation of Gen AI applications
LLM | Agentic | Security | Operations in one github repo with good links and pictures.
A comprehensive reference for securing Large Language Models (LLMs). Covers OWASP GenAI Top-10 risks, prompt injection, adversarial attacks, real-world incidents, and practical defenses. Includes catalogs of red-teaming tools, guardrails, and mitigation strategies to help developers, researchers, and security teams deploy AI responsibly.
Image text to text model, used with transformers.
Gated access
NeMo Helix: Make the agents you ship faster, more accurate, and safer.
A Python http(s) server designed to assist in red teaming activities such as receiving intercepted data via POST requests and serving content dynamically (e.g. payloads).
A professional AI security range for red teaming, vulnerability research, defensive validation, and hands-on AI/ML security training.
Image text to text model, used with transformers.
AI model security scanner. Grade your model A to F.
Runs in the browser on Hugging Face
Live chat plus exact Apple-Silicon MLX setup
Runs in the browser on Hugging Face
Score LLM red team findings for UAE bank go-live
Runs in the browser on Hugging Face