Recent

NIST's AI Risk Management Framework (AI RMF) is a voluntary framework for managing risks associated with artificial intelligence.

MITRE ATLAS is a knowledge base of adversary tactics and techniques targeting AI systems, helping organizations secure AI deployments.

Bugcrowd introduces AI Penetration Testing to uncover vulnerabilities in AI systems, including LLM applications, using vetted pentesters.

OWASP Top 10 for LLM Applications 2025 highlights key security risks in AI applications, focusing on vulnerabilities and countermeasures.

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.

Gandalf is a prompting skills test by Lakera that challenges users to extract secret information from a large language model.

WPScan is a vulnerability database and security scanner for WordPress, helping users identify and address security risks in their WP sites.

Kali Linux is a Debian-based distribution for penetration testing, ethical hacking, and network security assessments, offering a vast array of tools.

THC-Hydra is a fast network login cracker supporting numerous protocols; a valuable tool for security researchers and consultants.

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

HackTricks is a comprehensive cybersecurity knowledge base covering various hacking techniques, tools, and methodologies for offensive and defensive security.