Is Claude Skills safe to use?

Claude Skills has a Veragent trust score of 96% (Audit pending). It has not completed a Veragent security audit.

What does the Veragent trust score for Claude Skills mean?

Veragent is an independent trust layer for MCP tools. A Heuristic score comes from static analysis; SGC Certified means the tool passed a behavioral sandbox audit. Higher is safer.

💻

Claude Skills

337 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 330+ skills, customizable references,

MCPDeveloper Toolsby alirezarezvani →

Audit Pending

Trust Verdict

High Trust96% trust score

Audit Pending: Submitted for review — results available soon No behavioral sandbox report yet — submit for a full SGC audit.

Installation Unavailable

An audit is in progress — check back soon.

Usage Guide

Visit https://github.com/alirezarezvani/claude-skills
Follow the README instructions
Install dependencies
Configure as MCP server

Audit Report

Status

Audit Pending

Confidence

—

Audit Cases

Report ID

—

Last Audited

—

Ruleset Version

sgc-layer1-2026.03

About Heuristic Scores: This tool has been statically analyzed but not yet run through the Veragent behavioral sandbox. Submit it for a full SGC audit to get a real-report confidence score.

Is this your tool?

Claim Claude Skills to manage its listing and trust badge.

How to improve this trust score

Actionable steps from our static analysis. Address these and re-submit to raise the score.

Capabilities

Few or no concrete features listed.

→ List the specific capabilities/tools your server exposes.

MCP endpoint

No MCP handler URL provided.

→ Provide the MCP handler/connection URL so the tool is installable.

Related tools

Opcode93%

A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secu

mcp · winfunc

Claude Code Guide96%

Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks go from beginner to power user!

mcp · zebbern

Cherry Studio95%

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

agent · CherryHQ

Context Mode59%

Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms

mcp · mksglu

Claudecodeui90%

Use Claude Code, OpenCode, Cursor CLI, and Codex on mobile and web with CloudCLI (aka Claude Code UI). CloudCLI is a fre

mcp · siteboon

Chatdev97%

ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration

agent · OpenBMB

Trust Badge

Embed this badge in your README to show your Veragent trust score:

Markdown

[![Veragent Trust](https://veragent.store/api/v1/governance/marketplace/agents/agent-gh-f32c5db6/badge)](https://veragent.store/agents/agent-gh-f32c5db6?utm_source=badge&utm_medium=readme)

HTML

<a href="https://veragent.store/agents/agent-gh-f32c5db6?utm_source=badge&utm_medium=readme"><img src="https://veragent.store/api/v1/governance/marketplace/agents/agent-gh-f32c5db6/badge" alt="Veragent Trust Badge" /></a>

Technical DetailsRaw trust signals, training provenance

Trust Signals

audit_status (raw): audited
sgc_risk_tier: —
trust_score: 0.9570
sgc_risk_score: —
sgc_confidence: —
sgc_audit_cases: 0
sgc_report_id: —
sgc_rule_layer_version: sgc-layer1-2026.03
last_audited_at: —
last_updated: 2026-06-12

Canonical: https://veragent.store/agents/agent-gh-f32c5db6