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.

Open source prompt injection protection for Agents calling tools (via MCP, CLI or direct function calling). Detect and defend against prompt injection attacks. 22MB, CPU-only, < 10ms latency.

PromptMe is an educational project that showcases security vulnerabilities in large language models (LLMs) and their web integrations. It includes 10 hands-on challenges inspired by the OWASP LLM Top 10, demonstrating how these vulnerabilities can be discovered and exploited in real-world scenarios.

AgentWard – Built for all, hardened for OpenClaw.

Tamper-evident integrity monitor for the MCP config & server files your local AI agents load.

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization

An adversarially benchmarked reference implementation for pre-action AI agent authorization. Provenance-based gating for LLM agent tool calls: deny-by-default permissions, parameter lineage, signed receipts, audit logging.

Protect your LLMs from prompt injection and jailbreak attacks. Easy-to-use Python package with multiple detection methods, CLI tool, and FastAPI integration.

IntentFrame security plugin for Hermes Agent (Nous Research) — an external policy checkpoint that gates terminal, code, file, and cron tool calls before they run on your machine.

Detect and sanitize prompt injection attacks in Rails apps. Protects against direct injection (users hacking your LLMs via form inputs) and indirect injection (malicious prompts stored for other LLMs to scrape). ~70 detection patterns across 7 attack categories with configurable sensitivity levels. Now includes resource extraction detection pattern

A multi-layered prompt injection detection system built with Laravel.

🔥 QFIRE — a prompt firewall for LLM applications (proxy + CLI + benchmark harness) in Rust (100+ firewall rules).

A CLI-driven security proxy that scans every HTTP request for threats using the Citadel AI engine — paid per request via the x402 protocol.

A local-first agentic SOC & security watchdog for autonomous AI agents. Dual‑hemisphere Gemma 4 reasoning, behavioral drift tracking, event ledger, and kinetic response via the ButterVault. Protects OpenClaw, Hermes-Agent, and other MCP-based agents from prompt injection and rogue behavior.

Silent dependency injection through AI documentation pipelines. 240 isolated Docker runs proving Context Hub's zero-sanitization MCP server lets poisoned docs compromise developer projects without warning.

Transform any content into 9 platform-native formats or convert between content types — with optional brand voice matching. Supports Twitter/X, LinkedIn, newsletter, Instagram, YouTube Shorts, TikTok, Threads, Bluesky, and podcast. Secure-by-default: includes prompt injection defenses for safe URL and web content processing.

Counter-recon honeypot against agentic LLM attackers (PentestGPT/AutoGPT/LangChain). Six deploy modes: Flask drop-in, WSGI/ASGI middleware (Django/FastAPI), callable Python primitives, decoyshield CLI, edge configs (nginx/Caddy/Cloudflare), and Node.js npm package (Express/Fastify). Invisible-to-human, visible-to-LLM bait halts AI scans.

Belay is an open-source, local-first security layer for AI coding agents (Claude Code, Codex, Cursor, OpenClaw, Hermes Agent and MCP) that blocks dangerous commands, secret leaks, and prompt injection at the tool-call boundary in under 100ms — no LLM in the decision path by default, no cloud, no phone-home.

🤖 AI-powered Digital Marketing Assistant — content creation, strategy, research & analytics via Telegram. Bilingual EN/ID, Notion integration, pluggable LLM, security-hardened.