
system_prompts_leaks
Curated collection of extracted system prompts from major AI chatbots including Claude, ChatGPT, Gemini, Grok, and Copilot. Updated regularly with…

Curated collection of extracted system prompts from major AI chatbots including Claude, ChatGPT, Gemini, Grok, and Copilot. Updated regularly with…

High-performance SMT solver for automated theorem proving, constraint solving, and program verification. Supports multiple theories and language…

A comprehensive, step-by-step guide to mastering cybersecurity from beginner to expert level with curated resources, tools, and career guidance

Supply-chain Levels for Software Artifacts


Research code & papers from members of vx-underground.

Security Research from the Microsoft Security Response Center (MSRC)

AIL framework - Analysis Information Leak framework. Project moved to https://github.com/ail-project

Tracking interesting Linux (and UNIX) malware. Send PRs

Curated wordlists, hashcat rules, and masks derived from billions of real passwords, with statistical analysis and research slides from RootedCON…

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

Turn any collection of documents into a knowledge graph. Extract entities and relationships via LLM, deduplicate with your approval. Map domains,…

Evaluation framework for studying LLM agents that automatically generate working exploits from vulnerability reports, bypassing modern security…

Slide decks from my conference presentations

Reverse engineering NVIDIA SASS instruction dictionary, kernel audits and pattern recognition across GPU architectures.

I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in…

SpecterOps Presentations