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.
☆165Apr 3, 2026Updated 7 months ago
Alternatives and similar repositories for LLMSecurityGuide
Users that are interested in LLMSecurityGuide are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Open-Source autonomous security operations and red teaming agent built to help defenders investigate threats, analyze vulnerabilities, as…☆37Jun 25, 2026Updated 4 months ago
- Local workstation and network security with ContextCypher diagrams, threat analysis and GRC. Use standalone or through scoped MCP, CLI an…☆14Sep 9, 2026Updated 2 months ago
- The CoSAI Risk Map is a framework for identifying, analyzing, and mitigating security risks in Artificial Intelligence systems. As tradit…☆107Updated this week
- Track the lifetime of leaked secrets through git history - detect credential-shaped strings offline and report how long each stayed expos…☆31Oct 26, 2026Updated 3 weeks ago
- realistic mouse movement created by a generative AI trained on human mouse data to bypass web-based bot detection and highlight security …☆10Jun 30, 2023Updated 3 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assess…☆72Updated this week
- ☆14Mar 11, 2022Updated 4 years ago
- PromptMe is an educational project that showcases security vulnerabilities in large language models (LLMs) and their web integrations. It…☆112Sep 10, 2026Updated 2 months ago
- OWASP LLM Security Verification Standard☆59Oct 23, 2026Updated 3 weeks ago
- Curated LLM/AI attack tools — prompt injection, jailbreaks, agentic threats, adversarial ML, MCP attack surface☆17May 18, 2026Updated 6 months ago
- A curated list of research, frameworks, tools, evaluations, and resources focused on AI alignment, safety, robustness, red-teaming, model…☆16Sep 6, 2026Updated 2 months ago
- A recon Framework for Bug Bounty Hunters that would convert the output of a script into Markdown syntax document, which would help them t…☆12Sep 21, 2021Updated 5 years ago
- Runtime security for AI agents. In-process, zero dependencies, Apache 2.0.☆29Nov 12, 2026Updated last week
- ☆11May 10, 2023Updated 3 years ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Block abused TLDs in Tenant Allow BlockList☆18Sep 10, 2026Updated 2 months ago
- AI/ML/LLM Penetration Testing Toolkit by Mr-Infect — the #1 GitHub resource for AI security, red teaming, and adversarial ML techniques.…☆316Feb 19, 2026Updated 9 months ago
- Comprehensive AWS cloud reconnaissance and privilege escalation toolkit written in Python. Features IAM, EC2, S3, Lambda, ECS, Secrets Ma…☆50Jul 8, 2025Updated last year
- AI / LLM Red Team Field Manual & Consultant’s Handbook☆349May 8, 2026Updated 6 months ago
- Given a list of domains and known IP and buckets that are owned, which might be susceptible to domain hijacking?☆16Sep 20, 2024Updated 2 years ago
- All things specific to LLM Red Teaming Generative AI☆31Oct 22, 2024Updated 2 years ago
- AI hacking snippets for prompt injection, jailbreaking LLMs, and bypassing AI filters. Ideal for ethical hackers and security researchers…☆152Jun 4, 2026Updated 5 months ago
- Living off the Land (LOL) attack techniques, tools, and defender resources☆46May 1, 2026Updated 6 months ago
- 🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. R…☆31Oct 24, 2026Updated 3 weeks 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.
- Essential playbooks & runbooks for cybersecurity operations. A dynamic resource for security pros to navigate digital threats, with best …☆20Jun 23, 2026Updated 4 months ago
- Security-testing methodology as portable, tool-agnostic agent skills for Claude Code and any agent runtime: white-box bug hunting, AI-age…☆27Sep 8, 2026Updated 2 months ago
- ☆24Dec 16, 2024Updated last year
- Defensive cybersecurity LLM — companion training/eval pipeline for athena129/CyberSecQwen-4B on Hugging Face☆13May 9, 2026Updated 6 months ago
- Provides a collection of sandboxes, exploitation code, and tutorials that exemplifies GenAI Red Teaming exercises. It aims to help securi…☆79Nov 9, 2026Updated last week
- Installing wazuh agents Unified XDR and SIEM protection on Ludus Ranges☆11Apr 4, 2026Updated 7 months ago
- A tool for scanning public or private AMIs for sensitive files and secrets. The tool follows the research made on AWS CloudQuarry where w…☆117Nov 13, 2024Updated 2 years ago
- Project to build a top class library only and only for hackers for FREE.☆14Nov 6, 2026Updated 2 weeks ago
- A guide to LLM hacking: fundamentals, prompt injection, offense, and defense☆202Apr 14, 2023Updated 3 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.
- Repo for some CrowdStrike Falcon Real-Time-Response PowerShell scripts☆17Oct 24, 2022Updated 4 years ago
- ☆14Oct 11, 2020Updated 6 years ago
- Evaluate and compare SBOMs of Maven projects☆14Mar 3, 2023Updated 3 years ago
- A list of curated resources for people interested in AI Red Teaming, Jailbreaking, and Prompt Injection☆757Oct 29, 2026Updated 3 weeks ago
- Backdoor Collection 👾☆15Nov 14, 2026Updated last week
- ThreadsApp is a web application built with a purpose of helping people learn web application security.☆18Nov 22, 2024Updated last year
- ATT&CK Data Model (ADM): A TypeScript library for structured interaction with MITRE ATT&CK datasets. Uses Zod schemas, TypeScript types, …☆96Nov 11, 2026Updated last week
Are these results useful?