Diogo-Damasceno/AuthShield
Web Authentication Security Auditor - Automatically checks web apps for auth, session, CORS and JWT misconfigurations
Web Authentication Security Auditor - Automatically checks web apps for auth, session, CORS and JWT misconfigurations
Budget-aware context compilation and context firewall for tool-heavy AI agents.
Multi-Agent Harness for Production AI
Rules, skills, and scripts that teach AI agents how to contribute to open source projects
AI agent for autonomous cyber operations
Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, Codex, and Hermes.
Beginner-friendly open-source lab with good first issues for Git, GitHub, PRs, CI, TypeScript CLI, and maintainer practice.
🔌 188 ready connectors + any REST/SOAP/GraphQL/SQL system as custom connectors for Claude, ChatGPT and Copilot. Self-hosted, no-code, open source (AGPL-3.0). Learns how your systems connect.
Hack for LA's website
Aesthetic, minimalist platform for learning Japanese inspired by Duolingo and Monkeytype, built with Next.js and sponsored by Vercel. Beginner-friendly with plenty of good first issues - all contributions are welcome!
eBPF-based Networking, Security, and Observability
Cadastro de clientes com Servlet Java: formulario HTML (POST /cliente) -> Servlet -> validacoes + desafio extra
On-chain transaction graph analyzer + privacy/obfuscation simulator (EVM, read-only)
CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained tamper-evident event log, all exposed as a deny-by-default MCP server. Framework-agnostic, Python 3.11+.
Scans SSH keys, AWS credentials, and other credential files for unsafe permissions and ownership, with a CLI and TUI to fix them.
Self-OSINT: analisa o seu proprio numero de telefone (prefixo/pais/tipo/regiao) e checa registro em plataformas. MIT.
data.public.lu Model Context Protocol (MCP) server that allows AI chatbots to search, explore, and analyze datasets from the Luxembourg national Open Data platform, directly through conversation.
Local, monitor-first observability for AI agents: processes, file activity, TCP endpoints and attribution evidence. Windows primary; macOS/Linux experimental.
Self-hosted external attack surface scanner. Subdomain enumeration + takeover detection, ports, CVEs, TLS, SSH, web vulns, EPSS/KEV prioritisation. 19 tools across 6 phases, one `docker run`. MIT-licensed.
Responder is a LLMNR, NBT-NS and MDNS poisoner, with built-in HTTP/SMB/MSSQL/FTP/LDAP rogue authentication server supporting NTLMv1/NTLMv2/LMv2, Extended Security NTLMSSP and Basic HTTP authentication.
Hunt down social media accounts by username across social networks
claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.
Verificador defensivo de vazamento de senhas via k-anonymity (HIBP range API + modo offline por arquivo)
Scanner de rede inteligente: hosts, portas, deteccao de SO, SQLite e relatorio HTML
Mants Brand Orchestrator — plataforma de orquestração de branding para ChatGPT (Mants Company). Monorepo pnpm com web Next.js, extensão Chrome WXT e motor de prompts determinístico sem LLM.
Agente de pentest autonomo com IA plugavel: recon nao destrutivo com trava de autorizacao
Honeypot SSH/HTTP de baixa interacao: registra IPs, credenciais, User-Agent e gera estatisticas
Analista de malware estatico: hashes, entropia (packing), strings, IOCs e APIs suspeitas