Tag

Prompt Airlines AI CTF by Wiz challenges users to manipulate an AI chatbot for a free ticket, focusing on AI security vulnerabilities.

Payloads and techniques for exploiting prompt injection vulnerabilities in AI/NLP models like ChatGPT, including direct and indirect methods.

PromptBench: A unified library for evaluating and understanding large language models, enabling quick model assessment and robustness testing.

Open-source LLM security testing framework for automated red teaming, prompt injection detection, and vulnerability scanning in AI agents and RAGs.

PyRIT is an open-source Python framework empowering security pros to proactively identify risks in generative AI systems.

Autonomous security research framework that turns Claude Code into an agent for adversarial code analysis, fuzzing, and exploit generation.

AI-driven pentesting platform automating hacker intuition to find vulnerabilities before exploits, reducing discovery costs.

AI-infused API Security solution for the entire API lifecycle, from discovery and posture management to threat protection, including AI Agents.

Offline security checklist & report generator with 200+ tests across web, cloud, WiFi, firmware, and AI security domains.

ShipSec Studio is an open-source security platform for red teams to build visual workflows for tool orchestration, recon, and vulnerability scanning.

End-to-end platform for AI security testing and automated red teaming. Identify vulnerabilities like prompt injection and data leakage across AI systems.

Agentic AI-powered continuous penetration testing as a service (PTaaS) platform that combines AI scale with human supervision.