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 Aug 25, 2026 · ★ 92
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.
Sato Score
72/100· HighHow open, active & verifiable — not a safety or returns grade.
- Maintenance & liveness
- 35/35
- Code transparency
- 14/20
- Interface verifiability
- 0/10
- Docs & demo
- 6/10
- Listing transparency & provenance
- 14/15
- Independent verification
- 3/10
Observed record — 57 daily checks since 2026-07-14
- Succeeded
- 57
- Failed
- 0
- Their error
- 0
- Unattributed
- 0
This is the share of our daily checks that succeeded — not an availability guarantee. A check can fail because the host was down, because our runner timed out, or because the network in between dropped it, and only the first of those is a fact about this project. Failures are split by what we can attribute; anything we cannot attribute is counted, not hidden. 49 of these checks predate 2026-09-01, when the probe counted a bot-block (HTTP 403) as a failure and recorded no reason for any failure. Rates spanning that date mix two definitions. Since then: 100%.
Details
- Chains
- Unknown
- Agent types
- Coding Agent, Developer Tooling, Registry, Skill
- Open source
- Partial
- Deploys as
- npxfrom project docs · 2026-06-25
- Works with
- Claude Code, Gemini CLI, Cursor, Kiro, Codex, Antigravity, OpenCode, AdaL +1from project docs · 2026-07-14
- Last checked
- 2026-09-08
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.
Where Agent Skills Hub fits
Related concepts: What Are Onchain Agents?, Onchain Agents vs Offchain Agents
Recent Activity
All news →Releases and posts from Agent Skills Hub, pulled from its GitHub and X.
Listing History
Recorded changes to Agent Skills Hub's listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.
- Sep 1, 2026Sato Score tier: Medium → HighScore 69 → 72.
- Aug 5, 2026Active again — shipped after a quiet spell
- Jul 14, 2026Enriched: docs url
- Jul 14, 2026Auto-enriched: supported integrations
- Jun 25, 2026Enriched: creator name, creator profile url, agent type, tags
- Jun 25, 2026Auto-enriched: deployment options, supported integrations
- Jun 11, 2026Sato Hub began tracking this listing
Related Resources
Coinbase AgentKit
ActiveCoinbase's toolkit for giving AI agents wallets and the ability to take onchain actions.
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.
Is this your project?
Prove you control the domain and you can correct this page — description, links, tags, chains. Claiming proves control, not verification: it doesn't change the Sato Score or mark anything as audited.
Claim this listing →Cite this page
Sato Hub. "Agent Skills Hub — Sato Hub." Sato Hub, updated 2026-09-08, accessed 2026-09-08. https://satohub.ai/resources/agent-skills-hubThis page is refreshed daily. Citations include the date so a reader can tell which snapshot a claim came from.
Join the Sato Hub Briefing
One email a week — the agents, tools, and infrastructure that actually shipped, and why they matter.