
Boucle-framework
Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

Ghostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack

Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

Spicy malware 0day. Full kill-chain malware: exploit, pivot, c2, persistence. Rust converted to pseudo-code - if you're smart you can build it…

Pupy is an opensource, multi-platform (Windows, Linux, OSX, Android), multi function RAT (Remote Administration Tool) mainly written in python. It…

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment

My experiments in weaponizing Nim (https://nim-lang.org/)

Tool to search secrets in various filetypes.

Exploit code for CVE-2020-11579, an arbitrary file disclosure through the MySQL client in PHPKB

A Powerful Penetration Tool For Automating Penetration Tasks Such As Local Privilege Escalation, Enumeration, Exfiltration and More... Use Or Build…

A simple utility to convert EXE files to JPEG images and vice versa.

Crawler (Bot) searching for credential leaks on paste sites.

:key: (THIS CODE IS OUTDATED FOR NEW CHROME VERSIONS) Decrypt chromium based browsers passwords, cookies, credit cards, history, bookmarks, autofill.…

The SteaLinG is an open-source penetration testing framework designed for social engineering

Analysis of malware found on a server compromised via CVE-2025-55182, including obfuscated dropper, C2 communication, persistence mechanisms, and…

CVE-2020-9992 - A design flaw in MobileDevice.framework/Xcode and iOS/iPadOS/tvOS Development Tools allows an attacker in the same network to gain…

AI Prompt Secret Scanner: local proxy and Claude Code hook that blocks secrets before they reach AI APIs