
confirmesc
Linux privesc enumerator that confirms exploitability and gives you the exact root shell command - no GTFOBins searching. MCP server + AI-agent…

Linux privesc enumerator that confirms exploitability and gives you the exact root shell command - no GTFOBins searching. MCP server + AI-agent…

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

Kernel-enforced authority and runtime security for Linux systems, autonomous software, and AI agents.

Trained to Escalate: Forensic Analysis and Local Replication of RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)

Forensic Analysis and Local Replication of the OpenAI-Artifactory Privilege Escalation Incident (CVE-2026-65616)

Autonomous LLM red team agent that plans and executes full attack chains—recon, exploitation, privilege escalation, lateral movement and C2—inside an…

Network and domain security auditor scanning Windows Active Directory, Linux systems, and network infrastructure with AI-powered hardening guides…

AI-powered penetration testing assistant using local LLM on linux (Parrot OS)

AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual…

Reverse engineered Linux kernel driver and userspace library for the Apple Neural Engine (ANE), enabling hardware access and analysis on Linux…

Provenance-aware Linux kernel vulnerability research harness used in the investigation of CVE-2026-53075

A technical case study and timeline dataset documenting Google Gemini 2.5 Pro's safety alignment policies, guardrails, and refusal behavior evolution…

Autonomous Rust endpoint security agent combining Ring-0 Windows driver and Linux eBPF pre-execution blocking, YARA detection, MITRE ATT&CK mapping,…

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

Red team framework and multi-operator C2 platform with AI agents, malleable implants, rootkits, phishing engine, and 741 CLI commands covering the…

Proper sandboxing for agentic coding and web browsing

KLAIOS is a hybrid security environment that merges Kali Linux’s offensive toolkit with hardened, VPN-bunker-style isolation—enhanced by modern AI…

Artefacts for blog post on finding CVE-2025-37899 with o3