pentest

A research framework that trains custom LLMs (Qwen 14B with reinforcement learning) on curated penetration-testing reasoning datasets to autonomously generate pentest strategies and step-by-step actions. Ships dataset-collection utilities, training code, RL experiments, and CTF-based evaluation, with an accompanying arXiv preprint.

Academic (TU Wien ipa-lab) open-source framework for building LLM-driven autonomous pentest agents in under ~50 lines, covering Linux privilege escalation, web-app and REST-API testing via SSH/local shell. Includes SQLite run logging and a web viewer for replaying agent runs; supports OpenAI and local models.

Open-source pentest assistant that pairs the WhiteRabbitNeo security LLM with the PentestGPT prompting methodology, using structured todo-list workflows and constrained (outlines) generation to keep the fully-open-source stack usable without proprietary APIs. Author notes parity with GPT-4 is still a work in progress.

Claude Code plugin marketplace of 45 installable plugins (110 skills) covering pentest, threat modeling, detection engineering, DFIR, GRC and LLM/agentic-AI security, with role bundles such as pentester that auto-install their parts.

A set of Claude Code subagents, each a domain-specific system prompt for penetration testing, installed as agent files or a plugin, offering an advisory mode and a scope-gated mode that composes and runs tools.

A large, widely-used index of curated security awesome-lists for hackers, pentesters, and researchers, spanning 50+ domains including web hacking, bug bounty, malware analysis, OSINT, Android, IoT, forensics, and cryptography.

The OWASP Mobile Application Security Testing Guide: a comprehensive manual for mobile app security testing and reverse engineering on Android and iOS. Covers static and dynamic analysis, runtime and network-traffic analysis, cryptography testing, and mobile penetration-testing methodology, mapped to the OWASP MASVS standard and MASWE weakness enumeration.

A pentesting and VAPT/AppSec knowledge base spanning 23 security domains (web, mobile, API, cloud, network, LLM, MCP security), aggregating methodologies, 100+ reference PDFs, 200+ tools organized by category, and an AI-assisted pentest agent skill.

A curated index of resources on applying LLMs to automated penetration testing: 105+ academic papers grouped into systems/agents, benchmarks/cyber-ranges, empirical evaluations, surveys, and defense/ethics, plus links to code repositories (PentestGPT, VulnBot, Shannon and others) and evaluation benchmarks. Tied to the paper 'Hackers or Hallucinators?'.

A study/reference repository for OSCP exam preparation with command references organized by tool (Nmap, Hydra, Hashcat, Wfuzz, Cewl), technique notes on reverse shells, privilege escalation, Active Directory, buffer overflow, SQLi and XSS, plus write-ups from HackTheBox, VulnHub, Proving Grounds and TryHackMe.

A curated, security-specific directory of ~200+ open-source bug-bounty and pentest tools organized by phase and vulnerability class: reconnaissance (subdomain enum, port scanning, content discovery), exploitation (SQLi, XSS, XXE, SSRF, CSRF, command injection), and specialized scanning (JWT, S3 buckets, CMS, WAF evasion). CC0-licensed.

A curated collection of hacking, penetration-testing, and AI red-teaming learning resources: educational courses, YouTube channels, skill-building platforms (HackTheBox, TryHackMe, CTFs), reverse-engineering/privesc/OSINT/malware-analysis training, vulnerable practice apps, exploit databases, and pentest distros (Kali, ParrotOS, BlackArch).

A structured penetration-testing knowledge base by the WgpSec team, packaged for consumption by AI agents: 200+ attack-chain methodologies (recon through post-exploitation, cloud, code audit, CTF, malware analysis, lateral movement), password/fuzzing dictionaries, exploit payloads for SQLi/XSS/SSRF, and a 600+ entry vulnerability database organized by product. It is the knowledge layer of the WgpSec agentic pentest ecosystem (MCP server + autonomous agent).