#pentesting

实战 SRC / 众测 / Bug bounty 漏洞挖掘 Claude Code skill — 19 个攻击类 playbook、305 个结构化 payload、263 个 WAF/EDR 绕过、2887 份 HackerOne 真实案例、88,636 WooYun 案例统计

SECS (SECurity aSsistant) turns an AI coding agent (Claude Code, Cursor, Codex) into an authorized information-security assistant - 35 security Agent Skills, a Debian/Ubuntu/Kali toolchain installer, and a local Metasploitable 3 practice lab, under strict rules of engagement.

Decepticon 2026: AI Red Team Toolkit 🔓 | Autonomous Security Agent

The complete security auditor for Claude Code — web, API, mobile, cloud, wireless, code, secrets, dependencies, IaC, containers and LLM apps. Token-optimised, exploitation-ranked, self-updating.

Detect when Claude silently falls back from Fable 5 to Opus 4.8, log it to a local tamper-evident ledger, and keep your work on the frontier model.

Security testing skill for OS command injection and argument injection. Claude Code skill format.

Local-first Burp Suite MCP extension for HTTP, WebSocket, Scanner and Collaborator workflows, with operator controls and complete AI activity auditing.

Configuración de Claude Code para pentesting — máquinas de HTB y programas de bug bounty.

AI-powered vulnerability analysis platform that transforms Nmap XML scans into actionable security findings with CVE enrichment, risk scoring, PDF reporting, and a Flask dashboard.

A command-line red-team scanner for LLM agents. 21 techniques, zero dependencies, reports as JSON, SARIF or Markdown. Every finding carries the prompt and reply behind it.

Projet de Fin d'Études en cybersécurité : plateforme de simulation Attaque/Défense (Red Team & Blue Team) sous Unix. Pentest avec Nmap, Metasploit et Hydra, durcissement système et pare-feu, supervision SIEM via Wazuh, scripts Bash d'automatisation (détection/réaction) et analyse des alertes par IA (API Claude).