juice-shop

OWASP Juice Shop...

dotclaude-security

dotclaude-security Scan a repo's local .claude/ config — settings.json hooks, MCP server defs, env blocks, permissions.allow — for the RCE and API-key-exfiltration footguns that fire the moment you git clone and open an untrusted repository in Claude Code. It points at the exact dangerous line so...

database-sentinel

🛡️ Database Sentinel A Claude Skill that audits your database backends for security vulnerabilities. Drop it into Claude Code, Cursor, or any Claude-powered environment. Say "audit my database" and get a comprehensive security report with exact fix code — in minutes, not days. 170+ Lovable apps...

Agentic-Bug-Hunter

BugHunter Охота за багами с помощью ИИ — от разведки до отчёта, прямо в вашем терминале. Бесплатная настройка · Быстрый старт · Команды · Что он находит · Установка · FAQ !BUGHUNTER — конвейер автоматизации Bug...

lisa.py

Integración MCP de LLDB Este proyecto proporciona una integración del Protocolo de Contexto de Modelo MCP para LLDB, permitiendo que asistentes de IA como Claude interactúen con tus sesiones de depuración a través de una interfaz estandarizada. Descripción general La integración consta de dos...

claude_opus_cve_2023_0266

Demonstration that Claude 3 Opus does not understand CVE-2023-0266 and does not find it Demo 1. Even if told where the bug is Opus does not find it, and hallucinates the presence of lock acquisitions Demo 2. "Prompt engineering" aka telling the LLM exactly how to find the bug also doesn't work De...

CVE-2026-Pending-Claude-Desktop-RCE

This repository does not have a README...

yolo-cage

yolo-cage: autonomous coding agents that do no harm You're a responsible engineer. You'd never just let an AI run roughshod through your most sensitive systems and codebases. That's why you'd never just shut off the safeguards for a tool like Claude Code. It asks permission for every dangerous...

red-clippy

Red Clippy Your agent tests. Red Clippy keeps the record. Open-source pentest management built to be operated by an AI agent. Connect it to Claude Code over MCP and it runs the engagement alongside you: scope and assets, recon observations, methodology coverage, and findings with CVSS and evidenc...

shai-hulud-scan

shai-hulud-scan Ein Claude Code-Skill, der Maschinen auf Anzeichen einer Kompromittierung IOCs durch den Mini-Shai-Hulud -Supply-Chain-Wurm CVE-2026-45321, CVSS 9.6 scannt. Was ist Mini Shai-Hulud? Ein sich selbst verbreitender Supply-Chain-Wurm, der am 11. Mai 2026 über 170 npm/PyPI-Pakete...

write-ups

write-ups RCE in Github Desktop v2.9.4 RCE tramite gh run download GitHub CLI Claude Code: esecuzione di codice non sandboxed da prompt injection tramite confusione del worktree .git — CVE-2026-55607...

aiagent-detection-rules

aiagent-detection-rules Sigma-, Splunk-, Elastic- und YARA-Erkennungsregeln für den Claude-Code-Quellcode-Leak 31. März 2026 und den gleichzeitigen npm-Lieferkettenangriff. Am 31. März 2026 hat Anthropic versehentlich eine fehlkonfigurierte Source-Map in @anthropic-ai/[email protected]...

sentinel-cve

🛡️ Sentinel — Spiegatore CLI per CVE "Questa CVE mi riguarda?" — risposta in secondi, non ore. Sentinel prende un ID CVE, recupera dati da NVD, OSV.dev e MITRE, poi usa Claude per produrre un briefing chiaro e attuabile in 5 sezioni sulla vulnerabilità. Installazione root@kitploit: cd sentinel/ pi...

honeyslop

honeyslop - canary di codice per smistare rapidamente i report di vulnerabilità allucinati "slop" honeyslop è un insieme di canary di codice, esche, per progetti open-source sommersi da report di vulnerabilità allucinati dall'IA "slop" e non verificati. Con questa iniezione di rumore avversario,...

safer-dependencies

Sicherere Abhängigkeiten für Claude Code Wenn KI-Codierungsassistenten wie Claude Pakete zu deinem Projekt hinzufügen, wählen sie oft einfach eine Version, die sich richtig anhört – ohne zu prüfen, ob sie bekannte Sicherheitsschwachstellen aufweist, ob das Paket noch aktiv gepflegt wird oder ob d...

CVE-2025-59536

CVE-2025-59536 - a implementação do diálogo de confiança de inicialização. Vulnerabilidade do Claude Gravidade: ALTA CVSS: 8.8 Impacto: Confidencialidade, Integridade, Disponibilidade Publicado: 2025-10-03 Legal Apenas para testes de segurança autorizados. Causa Raiz versão curta Claude Code é um...

ctf-skills

ctf-skills Agent Skills per risolvere sfide CTF — exploit web, pwn binario, crittografia, reverse engineering, analisi forense, OSINT e altro ancora. Funziona con qualsiasi strumento che supporti la specifica Agent Skills, incluso Claude Code. Installazionebash npx skills add ljagiello/ctf-skills...

pentest-ai-agents

pentest-ai-agents 50 Claude Code-Subagenten für Penetrationstests. Schnellstart | Spickzettel | Abdeckung | Agenten | Beispiele Inhaltsverzeichnis Neuerungen in v3.3 Neuerungen in v3.2 Agentenübersicht Neuerungen in v3.1 Schnellstart Spickzettel Abdeckung...

cve-2026-45033-class

Claude Code — Guard-Bypass für Git-Bare-Repo / core.fsmonitor PoC Proof-of-concept für die Schwachstellenklasse „bösartiges Bare-Git-Repository →core.fsmonitor → Codeausführung" vgl. CVE-2026-45033 in GitHub Copilot CLI, reproduziert gegen Claude Code , wobei die zusätzliche...

claude-project-scanner

Scanner di progetti Claude Skill di Claude Code in sola lettura che analizza progetti di terze parti per individuare rischi di sicurezza noti prima di aprirli. Rileva i pattern di attacco documentati in: CVE-2025-59536 Claude Code Lifecycle Hooks injection CVE-2025-61260 OpenAI Codex CODEXHOME...