
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.

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

Code written as part of our various malware investigations

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

This page is a result of the ongoing hands-on research around advanced Linux attacks, detection and forensics techniques and tools.

An LLVM-based instrumentation tool for universal taint tracking, dataflow analysis, and tracing.

Windows host hardening auditor and remediation tool in PowerShell: CIS, DISA STIG, Essential Eight checks, reversible fixes, optional AI analysis

Container escape proof-of-concept exploits for CVE-2026-80521 and CVE-2026-52910, with a disposable QEMU/Ubuntu VM harness for safe PoC execution.

Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)

Evidence and data for the Sorami technical report on security defaults of 15 AI serving, vector database and MCP Helm charts on Kubernetes.

OWASP knowledge base and validator for HTTP security response headers, providing recommendations, statistics, and automated configuration checks.

Comprehensive open-source book on SELinux covering kernel components, userspace libraries, policy toolchain, and policy language. Includes build…

Cryptographically signed, replay-verifiable evidence layer for AI agents. Governs actions in the loop, produces Ed25519-signed receipts linked into a…

:robot: NO, There is an easy way to exploit this vulnerability! (vibecoded to prove a point)

A centralized resource for previously documented WDAC bypass techniques

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


GNU IFUNC is the real culprit behind CVE-2024-3094