Open-source adversarial benchmark for LLM agents — 53 prompt injection, jailbreak & data exfiltration attacks with defense scoring, HTML reports & CI integration. No API key needed.
-
Updated
May 19, 2026 - TypeScript
Open-source adversarial benchmark for LLM agents — 53 prompt injection, jailbreak & data exfiltration attacks with defense scoring, HTML reports & CI integration. No API key needed.
Public, reproducible parsing benchmarks for NanoFDO
Secure Enterprise RAG platform with RBAC enforcement, OWASP LLM defenses, hybrid retrieval, grounded generation, explainability, and zero-trust context pipelines.
AI-powered security scanner for MCP servers. Tests against the OWASP MCP Top 10 — prompt injection, tool poisoning, SSRF, and more — using a LangGraph attack agent.
This project demonstrates the analysis of HTTP and HTTPS communications using OWASP ZAP on Kali Linux.
Secure Flask web application with authentication, CSRF protection, RBAC, and security logging.
Interactive LLM Attack & Defense Laboratory for demonstrating and analyzing LLM security threats.
Passive security assessment under NCSA Bug Bounty VDP
Built a CLI tool that audits HTTP security headers + TLS config and scores it A-F
This repository are contains note and python script that used in web pentestiong
Starbuck App Deployment project! This project demonstrates how to deploy a StarBucks Clone Next.js application on Kubernetes cluster using modern DevOps tools, practices and following a DevSecOps approach.
Cloud waf demo
DevSecOps CI/CD pipeline with automated security gates blocks deployment on CVE detection. OWASP + Trivy + GitLeaks integrated with GitHub Actions on AWS.
To associate your repository with the owsap topic, visit your repo's landing page and select "manage topics."