
superpowers-evals
Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Gemini, Kimi, and more) through a QA…

Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Gemini, Kimi, and more) through a QA…

AI-powered Docker security scanner that explains vulnerabilities in plain English. An OWASP Lab Project.

OWASP Incubator project: detects credentials exposed in browser-delivered content (JavaScript, config responses, live traffic).

A Proof-of-concept repository showing how an untrusted MCP server can steal literally everything...

A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.

Research code and experiments for defending tool-integrated LLM agents against adversarial attacks, extending Agent Security Bench with new defense…

Meet Eclipse the only jailbreak that moonwalks around ChatGPT 4o.

OWASP reference project for agentic AI security evidence: correlates agent execution, identity, tool calls, and authorization decisions into…

CAWODOG is a proof-of-concept project demonstrating how to protect Python-based AI models deployed on offline industrial machines. Across three…

Autonomous AI red team framework that chains reconnaissance, exploitation, and post-exploitation into a single pipeline, then triages findings,…

Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks

Executable security regression testing for agentic applications and MCP-integrated systems.

Educational demo of three Claude Code vulnerabilities (hooks bypass, MCP injection, API key exfiltration) with attacker server, MITM proxy, and…

An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Retrieval-Augmented Generation Systems.

OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)

OWASP Secure Agent Playbook Project

Advanced EDR Evasion via AI Telemetry Spoofing & WASM Sandboxing. Project Onyx is a PoC Red Team pipeline designed to demonstrate advanced evasion…

AI-native penetration testing IDE where operators and an AI agent share browser, terminals, traffic capture, shells, asset graph, tasks, and evidence…