by vectra-ai-research · Agent Tool · ★ 365
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
docker run -d --name halberd -p 8050:8050 ghcr.io/vectra-ai-research/halberd:main
git clone https://github.com/vectra-ai-research/Halberd.git
Taken from the project's README on GitHub.
Flagged: sudo usage. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 365 |
| Forks | 40 |
| Language | Python |
| Category | Agent Tool |
| License | GPL-3.0 |
| Quality Score | 68/100 |
| Open Issues | 8 |
| Last Updated | 2026-04-08 |
| Created | 2024-03-06 |
| Platforms | aws, python |
| Est. Tokens | ~220k |
Halberd: Multi-Cloud Agentic Attack Tool Validate your multi-cloud defenses through realistic attack emulation 🚀 Get Started • 📖 About • ✨ Features • 📚 Guide • 📋 Docs • 🤝 Contributing 🚀 Quick Start Get Halberd running in under 60 seconds. Choose the installation method that works best for you. Option 1: Docker (Recommended) The fastest way to get started.
These tools work well together with Halberd for enhanced workflows:
Looking for a Halberd alternative? If you're comparing Halberd with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Terraform Skill for Claude Code and Codex. LLMs hallucinate a lot with Terraform - TerraShark fixes this. It e
The ultimate framework for building internal tools with LLM code generation by unifying front-end and back-end
An AI red-team agent for authorized labs and web app pentesting workflows. Turns Claude Code / OpenCode / Code
Cloud FinOps Skill & MCP by OptimNow. FinOps Foundation aligned knowledge for AI agents: cloud cost (AWS/Azure
A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integrati
Data API builder provides modern REST, GraphQL endpoints and MCP tools to your Azure Databases and on-prem sto
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: