
AI-Infra-Guard
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

Automated Penetration Testing Agentic Framework Powered by Large Language Models

📡 Comprehensive collection of OSINT tools for cybersecurity professionals, researchers, and bug bounty hunters. Topics: information gathering,…

Curated collection of cybersecurity resources, labs, and training materials covering ethical hacking, penetration testing, exploit development,…

Device-specific Android kernel exploit for CVE-2026-64560 on OnePlus 13 builds, providing temporary root via ADB shell with verified payloads and…

Reverse engineering the BYD Dolphin head unit — CAN bus, AVAS, NFC keys, OTA, and more. DiLink 3 / Android 10.

AI-assisted research pipeline that extracts HTTP desync techniques, generates malformed request test-cases, validates them via Burp, and confirms…

Temporary Root Research on Poco M7 Plus (SM6375) via Qualcomm GBL Exploit (CVE-2026-24088) + GhostLock Kernel Analysis (CVE-2026-43499)

Reverse engineering framework with disassembly, decompilation, taint analysis, version diffing and semantic search, plus LLM-driven autonomous binary…

OWASP framework cataloging the top 10 security risks in neocloud and AI data center infrastructure, covering hardware, networking, isolation,…

OWASP Incubator project: detects credentials exposed in browser-delivered content (JavaScript, config responses, live traffic).

A curated list of resources related to Industrial Control System (ICS) security.

Code written as part of our various malware investigations

Toolkit for exploring Linux kernel race conditions using KCOV traces: GUI and terminal viewers for concurrent execution and memory access, plus…

Honor WIN RT (AAK-AN00) CVE-2026-43499 temporary root - research notes

Reference implementation for "Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution". Out-of-band Epistemic Andon Cord,…

Security research write-up on exploiting CVE-2026-43499 on the Amazon Fire TV Stick 3rd Gen (sheldonp), from temporary root to bootloader unlock.

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