ChatGPT Jailbreaks, GPT Assistants Prompt Leaks, GPTs Prompt Injection, LLM Prompt Security, Super Prompts, Prompt Hack, Prompt Security, Ai Prompt Engineering, Adversarial Machine Learning.

The fastest Trust Layer for AI Agents

Mithra Scanner is an interactive API testing tool for prompt injection, refusal detection, and LLM security benchmarking. It supports YAML-based rule definitions, custom refusal lists, REST API integration, and provides detailed CLI output for security testing of language model endpoints.

MINOTAUR: The STRONGEST Secure Prompt EVER! Prompt Security Challenge, Impossible GPT Security, Prompts Cybersecurity, Prompting Vulnerabilities, FlowGPT, Secure Prompting, Secure LLMs, Prompt Hacker, Cutting-edge Ai Security, Unbreakable GPT Agent, Anti GPT Leak, System Prompt Security.

Bullet-proof your custom GPT system prompt security with KEVLAR, the ultimate prompt protector against rules extraction, prompt injections, and leaks of AI agent secret instructions.

The LLM guardian kernel

"Universal AI security framework - Protect LLM applications from prompt injection, jailbreaks, and adversarial attacks. Works with OpenAI, Anthropic, LangChain, and any LLM."

🚀 Unofficial Node.js SDK for Prompt Security's Protection API.

LLM Penetration Testing Framework - Discover vulnerabilities in AI applications before attackers do. 100attacks + AI-powered adaptive mode.

Universal Prompt Security Standard (UPSS): A framework for externalizing, securing, and managing LLM prompts and genAI systems, inspired by and extending OWASP OPSS concepts for any organization or project.

CloakPrompt is a CLI tool that redacts secrets (passwords, API keys, credentials, etc.) before sending data to AI models.

🛡️ Enterprise-grade AI security framework protecting LLMs from prompt injection attacks using ML-powered detection

Single-context metacognitive security framework for LLM prompt injection defense

carapex — A Python security boundary for LLM applications. Input is normalised, checked, and verified before reaching the model. Output is checked before reaching the caller. Security is baked in, not bolted on.

Live AI security demo: MCP tool abuse attacks vs Prompt Security defense, side-by-side in real time

Industrial LLM agents, prompt safety, and orchestration

Static analysis CLI that scans codebases for LLM prompt-injection, data-exfiltration, jailbreak, and unsafe agent/tool vulnerabilities. Runs fully offline, integrates with CI/CD, and outputs console, JSON, and SARIF reports.

CostGuardAI — an AI prompt preflight SaaS that predicts token usage, cost, and failure risk before submission and optimizes prompts to prevent truncation and overbilling.

Behavioral persona GPT modeled after a logical diagnostician. Engineered to audit user reasoning, minimize cognitive bias, and challenge assumptions with high-precision critique. (Inspired by the deductive reasoning of Dr. Gregory House).

Lint your AI coding sessions. Define rules, check compliance, get verdicts.