Starred repositories
A multi-provider, multi-agent orchestrator that organizes agents into a visual authority hierarchy.
Automated Αll-in-One OS command injection exploitation tool.
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Fast terminal UI for your SSH hosts: fuzzy-search and connect in two keystrokes, dual-pane SFTP file transfer, and background port forwarding. Keeps its own host database and generates the ssh com…
Six Claude Code plugins for the work that keeps coming back: repo maps, conditional rules, ticketed parallel work, extra subscription models, local usage metrics, and guided setup.
Sandboxed multi-scanner security for AI skills, MCP servers, and package trees — coverage honesty, SIE judging, heatmap posture, guided triage and fix. Scan what agents install; fail closed.
AI/ML and Generative AI Security Assessment Framework for AWS. Automatically audit Amazon Bedrock , SageMaker ,AgentCore, and Agent Registry workloads for security best practices
A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.
CrowdSec Skill : Install, configure, debug and operate crowdsec
A skill to help cybersecurity folks update and tweak their resume
Sandboxed devcontainer for running Claude Code in bypass mode safely. Built for security audits and untrusted code review.
A CLI tool for managing DigitalOcean droplets with automated setup, SSH configuration, and lifecycle management.
Opinionated defaults, documentation, and workflows for Claude Code at Trail of Bits
Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows
An empirical security testbed evaluating prompt injection, confused-deputy vulnerabilities, and tool-calling defenses in LLM agents.
Research code for the paper "The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers" https://arxiv.org/abs/2602.03085
A website that behaves as a Linux shell with features as pipes, redirects, globs, history, in-memory filesystem, plugin commands, themes. Static, no backend.
Notes of the book System Desgin Interview - An Insider's Guide
Lightweight, S3-compatible object storage server with built-in web dashboard. Single binary, low memory, encryption at rest.
use at own risk, SIGINT is more complex than just turning off a few things.....
A font-based deception tool for red teaming, security research, and whatever else.
Agent-ready DevOps, security, infrastructure, and compliance knowledge base with 80+ skills across Kubernetes, Terraform, AWS/Azure/GCP, AI platform operations, container hardening, SOC2/ISO27001, …
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
An EDR POC for claude. Copyright (c) Xservus Limited