Agent Skills Hub
A registry of AI agent skills that applies automated source-code scanning and assigns security grades before installation.
Last release Mar 2, 2026 · Last commit Apr 26, 2026 · ★ 26
Overview
Agent Skills Hub is a curated registry/marketplace of AI agent skills and MCP servers that scans each skill's source code for vulnerability patterns (e.g. arbitrary code execution, credential leakage, unbounded file access) and assigns security grades. It targets developers building with Claude Code and similar agents, and works across OpenClaw, Claude Code, Gemini, Cursor, and others. The grade methodology is self-reported by the platform; 'verified' here means scanned by the platform, not independently audited.
Details
- Chains
- Unknown
- Agent types
- Coding Agent, Developer Tooling
- Open source
- Partial
- Last checked
- 2026-06-10
Marketplace Signals
No marketplace signals recorded for this resource yet.
Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.
Recent Activity
All news →Releases and posts from Agent Skills Hub, pulled from its GitHub and X.
Related Resources
Hyperliquid
ActiveOnchain perpetual futures and spot DEX running on its own L1 with an HyperEVM smart-contract layer.
Model Context Protocol (MCP)
ActiveAnthropic's open standard for connecting AI systems to external tools and data sources.
1inch
ActiveMultichain DEX aggregator with a developer API suite and an official MCP server for AI-agent swap execution.
Join the Sato Hub Briefing
One email a week — the agents, tools, and infrastructure that actually shipped, and why they matter.