
nono
agent runtime security - zero trust, zero setup, zero latency agent sandboxing

agent runtime security - zero trust, zero setup, zero latency agent sandboxing

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and…

Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more

Hashcat rule analyzer and interpreter - A Rosetta Stone for decoding hashcat rule syntax

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

A tool which can be used to generate password list or dictionary from the details of the target

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

This repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.