
bx2-writeups
Cybersecurity writeups, walkthroughs, and technical notes by Nanashi Bx2.

Cybersecurity writeups, walkthroughs, and technical notes by Nanashi Bx2.
CVE-2026-20685 - Draft or TODO

AngularJS 1.x -> Angular 18 migration guidance for GitHub Copilot. Source-of-truth repo for…

AI-powered CLI tool that reviews code for security vulnerabilities, bugs, and anti-patterns using LLMs. Supports local and cloud providers, git…

Multi-layer security framework for AI agent ecosystems. Provides pre-installation skill auditing, file integrity monitoring, runtime protection, and…

PoC reproducer for CVE-2026-49042 (Apache Camel camel-langchain4j-tools): a prompt-injected LLM's tool-call arguments become unfiltered Exchange…

Advanced SQL Injection Scanner with AI-powered analysis, ethical compliance framework, and professional reporting.

Security standard for agent skills, providing guidelines and best practices to secure AI-driven autonomous agents in cloud and API environments.

TP Seguridad Informática UTN FRBA 2021

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

Public advisory landing page for CVE-2026-54519: missing ownership checks in ai-agent-automation memory APIs enabling cross-user memory read and…

Reference implementation of a multi-bit LLM watermarking scheme using coded payload spreading, unbiased reweighting, and soft-decision ECC decoding…

Intentionally vulnerable machine learning model for hands-on security training. Explore common ML vulnerabilities, adversarial attacks, and defensive…

Read-only safety scanner for Claude Code projects. Catches CVE-2025-59536, statusLine injection, prompt injection, and more.

CVE-2025-31337 Security Advisory - Critical Buffer Overflow in AI Chatbot Framework

Threat intelligence brief on CVE-2026-42208, a critical pre-auth SQL injection in BerriAI LiteLLM exploited within 36 hours of disclosure. Covers…

Black-box test whether an LLM chatbot is vulnerable to markdown/HTML exfil (CVE-2025-32711 class). Spins up a sink, sends payloads, renders in…

The Governed Agentic AI Operating System — Rust + Tauri 2.0 | 65 crates, 658 commands, 84 pages, 5,029 tests, 10/10 OWASP