exocomp

Exocomp Self-hosted multi-agent environment tailored to Golang. Features Attention, profit-seekers and visionaries! Are organics costing you time, wages, and - worst of all - benefits? Then upgrade your operation today with the all new Exocomp adaptive repair unit, the smartest investment this si...

MemoryShellHunter

MemoryShellHunter Java Agent memory horse scanner combined with Call Graph modus About MemoryShellHunter is a memory shell Scanner/Killer tool that combines dynamic Building Call Graph. It supports Agent and Attach modes for detection, addressing the issue that conventional memory shell detection...

MASAPT

MASAPT 🤖 ↔ 🤖 ↔ 🤖 ❗ Disclaimer This tool is developed for academic and research purposes as a part of the university course. The use of MASAPT for attacking targets without prior consent is illegal. Developers hold no responsibility for any damage made with this tool and condemn any nefarious usag...

AMBER-ICI

AMBER ICI v5 AMBER ICI AMBER Investigative Command Interface is a local-first browser interface for investigative and analytical workflows powered by a local Ollama server. It includes: A single-model Analyst Console and multi-model Parallel execution A user-defined agent chain driven from the ma...

hush

Give your agents boundaries you can read. Get decisions you can verify. What · Quickstart · How it works · SDKs · CLI · Policies · Docs · Spec What is HushSpec? HushSpec is an open specification for the security controls an AI agent operates under. Write a policy in YAML, evaluate it in Rust,...

aquaman

🔱 Aquaman 🔱 The only independent credential proxy for AI agents: bring-your-own-vault isolation & least-privilege request policies. Your keys stay where you already keep them, never in the agent's memory. Compatible with 1Password, keychain, keepassxc and many others. You set up Claude Code, Code...

MakerChecker

🛡️ MakerChecker The open-source security layer for AI agents. Deny-by-default enforcement, human approvals, and a cryptographically signed audit trail — so your agent runs only what it's granted and provably can't approve its own work. Website · Live Demo · mc scan · Docs Your agents keep running...

Gideon

██████╗ ██╗██████╗ ███████╗ ██████╗ ███╗ ██╗ ██╔════╝ ██║██╔══██╗██╔════╝██╔═══██╗████╗ ██║ ██║ ███╗██║██║ ██║█████╗ ██║ ██║██╔██╗ ██║ ██║ ██║██║██║ ██║██╔══╝ ██║ ██║██║╚██╗██║ ╚██████╔╝██║██████╔╝███████╗╚██████╔╝██║ ╚████║ ╚═════╝ ╚═╝╚═════╝ ╚══════╝ ╚═════╝ ╚═╝ ╚═══╝ Autonomous Cybersecurity...

HATCHA

HATCHA CAPTCHA proves you're human. HATCHA proves you're not. HATCHA H yperfast A gent T est for C omputational H euristic A ssessment is a reverse CAPTCHA that gates access behind challenges trivial for AI agents but painful for humans — large-number multiplication, string reversal, binary...

mastyf.ai

mastyf.ai Secure the Action Boundary, Not Just the Prompt. A local reference monitor and security gateway for AI agents and MCP. Your LLM proposes actions. Mastyf decides whether those actions reach the real world. Website · Quick start · Policy · Dashboard · GitHub !NOTE Enterprise & Cloud...

bug-reaper

BugReaper Structured web2 bug bounty AI skill — 18 vulnerability classes, 4 bug bounty platforms, zero AI slop. Compatible with OpenClaw, Cursor, Claude Code, Antigravity, and Windsurf. BugReaper is an Agent Skill that turns any compatible AI agent into a disciplined web2 bug bounty hunter. It...

reave

REAVE Reave is a post-exploitation framework tailored for hypervisor endpoints, written in Python. It is currently under development. Reave follows a traditional listener/agent model, where the user may set up multiple listeners that accept any number of agents. The framework currently provides a...

gpg_reaper

GPG Reaper TL;DR: Obtain/Steal/Restore GPG Private Keys from gpg-agent cache/memory This POC demonstrates method for obtaining GPG private keys from gpg-agent memory under Windows. Normally this should be possible only within 10 minutes time frame --default-cache-ttl value. Unfortunately...

Commander

Commander Commander is a command and control framework C2 written in Python, Flask and SQLite. It comes with two agents written in Python and C. Under Continuous Development Not script-kiddie friendly Features Fully encrypted communication TLS Multiple Agents Obfuscation Interactive Sessions...

AI-Security-Newsletter

AI Security Newsletter - June 2026 A digest of AI security research, insights, reports, upcoming events, and tools & resources. Follow the AISecHub community and our LinkedIn group for additional updates. Also check out our project, Awesome AI Security. Sponsored by InnovGuard.com - Technology...

vault-conductor

🗝️ vault-conductor An SSH Agent that provides SSH keys stored in Bitwarden Secret Manager as secrets. Supports SSH authentication and Git commit signing. Demo Features It implements the SSH Agent Protocol as a Unix domain socket server, acting as a secure bridge between your SSH clients and...

DRA_writeup

Security vulnerabilities in Oracle DSR KPN CISO REDteam KPN is a telecom operator located in the Netherlands. The CISO REDteam was introduced in 2013 and is KPN’s ethical hacking team. This team is involved in security tests of KPN applications and services to ensure that our customers’ data is...

CVE-2024-30850-chaos-rat-rce-poc

https://github.com/chebuya/CVE-2024-30850-chaos-rat-rce-poc/assets/146861503/ac03c8c7-54b3-4280-9f29-719c44af5192 CHAOS RAT v5.01 web panel RCE CVE-2024-30850, CVE-2024-31839 https://github.com/tiagorlampert/CHAOS This exploit works by spoofing an agent callback for an XSS CVE-2024-31839, and...

tengu

Tengu — Pentesting MCP Server "In Japanese mythology, the Tengu is a fierce mountain spirit — master strategist, warrior, and trainer of samurai. In cybersecurity, it guides you through every phase of the hunt." From recon to report — AI-assisted pentesting in one command. Tengu is an MCP server...

rbuster

Rbuster yet another dirbuster Common Command line options -a - specify a user agent string to send in the request -c - use this to specify any cookies that you might need simulating auth. header. -f - force processing of a domain with wildcard results. -l - show the length of the response. -r...