Basilisk — Open-source AI red teaming framework with genetic prompt evolution. Automated LLM security testing for GPT-4, Claude, Grok, Gemini. OWASP LLM Top 10 coverage. 32 attack modules.
☆88Oct 1, 2026Updated last month
Alternatives and similar repositories for basilisk
Users that are interested in basilisk are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- YWH Programs Selector is a CLI tool to filter bug bounty programs from platforms like YesWeHack☆11Jan 29, 2026Updated 9 months ago
- One-command confidential coding setup for Adverserial AI☆28Updated this week
- A diagnostic methodology for bypassing LLM defense layers — from input filters to persistent memory exploitation.☆67May 8, 2026Updated 6 months ago
- An app that rewrites its own code while you use it, and can't brick itself. Pi Durable + Worker Loader + Effect v4 + Foldkit on Cloudflar…☆14Nov 2, 2026Updated 2 weeks ago
- Comprehensive taxonomy of AI security vulnerabilities, LLM adversarial attacks, prompt injection techniques, and machine learning securit…☆21Sep 19, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- OWASP Hunting: Curated Payloads for Ethical Security Testing and Bug Bounty☆22Updated this week
- A comprehensive and hands-on workbook designed to sharpen your Active Directory penetration testing skills. Whether you're a red teamer, …☆21Feb 11, 2026Updated 9 months ago
- An interactive TLS-capable intercepting HTTP proxy for penetration testers and software developers.☆16Oct 26, 2026Updated 3 weeks ago
- All of our released books☆11Sep 19, 2026Updated 2 months ago
- Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks☆18Jul 13, 2026Updated 4 months ago
- A curated, auto-updated gallery of excellent reverse-engineering cases built with REA (reverse engineer anything) - refreshed daily by Gi…☆62Updated this week
- An uncensored local LLM interface built for security engineers. It enables private, filter-free interaction with abliterated models for v…☆26Oct 8, 2026Updated last month
- ARES - authorized red-team engagement automation with dashboard, campaign scope, module orchestration, OPSEC controls, encrypted vault, a…☆1,063Updated this week
- Brute-force decoder of BIP38 encrypted private keys☆11Nov 24, 2018Updated 7 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- AI-first external attack surface assessment with continuous discovery, evidence-based vulnerability validation, and developer-agent MCP i…☆743Updated this week
- ☆19Oct 19, 2026Updated 3 weeks ago
- Automated Red-Teaming tool for LLM Security. Evaluate system prompts against prompt injection, jailbreak, and data exfiltration attacks.☆18Mar 29, 2026Updated 7 months ago
- Curated list of public penetration test reports released by several consulting firms and academic security groups☆54Oct 31, 2017Updated 9 years ago
- Pollard, kangaroo method, based on engine VanitySearch1.15☆12Oct 9, 2019Updated 7 years ago
- Intentionally vulnerable LLM☆35Aug 24, 2026Updated 2 months ago
- WebSocket Penetration Testing Toolkit for Burp Suite☆33Mar 5, 2026Updated 8 months ago
- Thick client penetration testing and MSIX security audit toolkit for Windows. Audits .NET, Electron and native binaries: static and runti…☆25Updated this week
- PromptMe is an educational project that showcases security vulnerabilities in large language models (LLMs) and their web integrations. It…☆45Sep 10, 2026Updated 2 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- AI-powered adversary intelligence☆41Nov 6, 2026Updated last week
- ☆36Nov 11, 2026Updated last week
- HackAgent is an open-source security toolkit to detect vulnerabilities of your AI Agents☆541Updated this week
- 👻 ghost gpt– A powerful Termux-based penetration testing suite for ethical hackers. Includes free and premium tools to enhance your secu…☆30Aug 5, 2026Updated 3 months ago
- OWASP Top 10 Implemented in ASP.NET MVC☆16Mar 15, 2015Updated 11 years ago
- ☆11Mar 25, 2026Updated 7 months ago
- Pre-auth RCE PoC for WordPress core — chains CVE-2026-63030 (REST /batch/v1 route-confusion desync) with CVE-2026-60137 (author__not_in S…☆18Jul 22, 2026Updated 3 months ago
- Twi-Hack is a tiny RP2350A-powered hacking & prototyping dongle with USB-A/USB-C connectivity — your pocket-sized HID toolbox.☆11Apr 1, 2026Updated 7 months ago
- AI-powered security scanner for Claude Code plugins and skills - LLM analysis, static rules, taint tracking, CI/PR integration, and inte…☆15Mar 1, 2026Updated 8 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Inject code into .net applications☆14Nov 7, 2018Updated 8 years ago
- BINNY: an open source agent harness for reverse engineering. Plug in any model, or a local one.☆257Updated this week
- Master Repository for Multilogin X Automation, Browser Fingerprinting, and Stealth Scraper Solutions. Built by a Senior Automation Engine…☆19Jun 8, 2026Updated 5 months ago
- Neo4jWordlistHarvester but then with bloodhound json files☆13Jun 10, 2025Updated last year
- Research code for the paper "The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers" https://arxiv.org/abs/2602…☆50Mar 26, 2026Updated 7 months ago
- DeepTeam is a framework to red team LLMs and AI agents.☆3,110Oct 23, 2026Updated 3 weeks ago
- WiFi Pentest Kit is a toolkit designed for wireless network security testing and auditing. It provides utilities like deauth attack, evil…☆36Oct 9, 2026Updated last month
Are these results useful?