Xalgorix Autonomous AI Pentesting Agent 4.5.67

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

secbutler v0.2.2

Essential utilities for pentester, bug-bounty hunters and security researchers Features • Usage • Installation • License • secbutler is a utility tool made for pentesters , bug-bounty hunters and security researchers that contains all the most used and tedious stuff commonly used while performing...

nebula v2.0.0

Nebula AI Powered Pentesting The Zero Layer workbench Acknowledgement First, I would like to thank Almighty God, who is the source of all knowledge. Without Him, this would not be possible. Nebula brings the working parts of a security engagement into one desktop surface: terminal, code, browser,...

Xalgorix Autonomous AI Pentesting Agent 4.5.59

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

Xalgorix Autonomous AI Pentesting Agent 4.5.55

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

red-run_nexusHTB

Proof of concept for blacklanternsecurity'shttps://github.c...

blackbox-website-pentest-poc

PoC of blacbox pentesting about hand-on lab's...

Pentesting-Skill-For-Ai-Agent

No d...

cyber-ai-agent

╔══════════════════════════════════════╗ ║ CYBER-OMNI...

pharaohound

☥ Pharaohound ☥ The Fast-Triage, Command-Generating Active...

Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing

Large Language Models LLMs have shown promise for automated penetration testing, yet existing end-to-end black-box evaluations are highly susceptible to error cascading: failures in early reconnaissance can mask an agent's actual ability to exploit vulnerabilities. To more accurately characterize...

ARES

Ares — AI Penetration Testing Engine Autonomous AI pentesting...

sentinelx

sentinelx SentinelX AI — Next-gen AI-powered cybersecurit...

Grimoire

書 — The Pentesterʼs Spellbook Answer the questions. Unleash th...

webstrike-framework

WebStrike — Automated Web Pentesting Framework Created by...

Exploit for Deserialization of Untrusted Data in Facebook React

CVE-2025-55182 — React2Shell Interactive exploitation tool...

Kali-setup

🛠️ kali-setup A single bash script that pulls in the 20 most-...

bug-bounty-reports

Bug Bounty Reports — Josef Basner Sanitized, redacted, resp...

Exploit for Missing Authentication for Critical Function in Cpanel

🚀 CVE-2026-41940 - cPanel/WHM Authentication Bypass Exploit...

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for predefined goals such as capture-the-flag, remote code...