Agent Skill Evaluator

Comprehensive security and safety evaluation system for agent skills (.skill files). Use when users provide GitHub URLs, website links, or .skill files for download and request security assessment, safety evaluation, or ask "is this skill safe to use." Evaluates prompt injection risks, malicious code patterns, hidden instructions, data exfiltration attempts, and provides actionable recommendations with risk scoring.

23 stars 2 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add JeredBlu/eval-marketplace

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add JeredBlu/eval-marketplace --skill agent-skill-evaluator
Manual install
git clone --depth 1 https://github.com/JeredBlu/eval-marketplace.git /tmp/eval-marketplace
mkdir -p ~/.claude/skills
cp -r /tmp/eval-marketplace/evaluator-tools/skills/agent-skill-evaluator ~/.claude/skills/agent-skill-evaluator

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Agent Skill Evaluator

## Overview

Automatically evaluate the security, safety, and trustworthiness of agent skills from GitHub repositories, websites, or direct .skill file URLs. This skill performs comprehensive assessments including prompt injection detection, malicious code analysis, hidden instruction scanning, and risk scoring to provide actionable recommendations before installing skills.

## When to Use This Skill

Use this skill when users:
- Provide a GitHub URL to a skill repository
- Share a website link where a skill can be downloaded
- Provide a direct link to a .skill file
- Ask "is this skill safe to use?"
- Request security assessment of a skill
- Want to evaluate safety risks before installing a skill
- Need to identify prompt injections or malicious patterns
- Ask about the trustworthiness of a skill source

## Tool Strategy

This skill works with available MCPs and tools through graceful degradation:

**For GitHub repositories**:
- **Priority**: GitHub MCP (if available) for direct repository API access
- **Alternatives**: Bright Data MCP (The Web MCP) or built-in web tools for scraping
- **Fallback**: User-provided file upload if direct access fails

**For websites and direct .skill file URLs**:
- **Priority**: Bright Data MCP (The Web MCP) for website scraping and content fetching
- **Alternatives**: Built-in web_search and web_fetch tools
- **Fallback**: User-provided file upload if direct access fails

## Evaluation Workflow
Read the full skill on GitHub

Details

Skill name
agent-skill-evaluator
Path
evaluator-tools/skills/agent-skill-evaluator/SKILL.md
Repo updated
3 February 2026

FAQ

What does the Agent Skill Evaluator skill do?

Comprehensive security and safety evaluation system for agent skills (.skill files). Use when users provide GitHub URLs, website links, or .skill files for download and request security assessment, safety evaluation, or ask "is this skill safe to use." Evaluates prompt injection risks, malicious code patterns, hidden instructions, data exfiltration attempts, and provides actionable recommendations with risk scoring.

How do I install the Agent Skill Evaluator skill?

Claude Code plugin: /plugin marketplace add JeredBlu/eval-marketplace. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Agent Skill Evaluator popular?

It lives in JeredBlu/eval-marketplace, which has 23 GitHub stars and 2 forks.

Related skills

MCP Evaluator

23

JeredBlu/eval-marketplace

Comprehensive security and privacy evaluation system for MCP (Model Context Protocol) servers. Use when users provide GitHub URLs to MCP servers and request security assessment, privacy evaluation, or ask "is this MCP safe to use." Evaluates security vulnerabilities, privacy risks, code quality, community feedback, and provides actionable recommendations with risk scoring.

AI, LLMs & Agents

Drpc Rpc Pi

23

drpcorg/drpc-agent-skills

Pi Agent-specific DRPC setup flow. Use alongside drpc-rpc when the user asks for blockchain data, DRPC setup, x402 API-key acquisition, Coinbase Payments MCP, pi-mcp-adapter, or when DRPC MCP is not configured in Pi.

AI, LLMs & Agents

Zopenclaw

46

zocomputer/skills

Install and run OpenClaw on Zo Computer with Tailscale private networking, browser Control UI, and Zo MCP tools via mcporter. Use this skill whenever the user wants to set up OpenClaw on their Zo, install OpenClaw, run OpenClaw, host OpenClaw, or asks about getting OpenClaw running on Zo. Also use when the user mentions "openclaw", "open claw", "personal agent framework", or asks about running a persistent AI agent on their Zo with Telegram/Discord/WhatsApp access. Handles Tailscale setup, OpenClaw installation, mcporter setup for Zo tools, two-phase gateway bootstrap, reprovision-safe service

AI, LLMs & Agents56

Vapi

46

zocomputer/skills

Voice AI integration with Vapi. Enables inbound/outbound phone calls with AI voice agents that can check calendars and book appointments.

AI, LLMs & Agents56

AI Ad Compliance Check

38

vargHQ/skills

Turns an AI video ad into a compliance report for TikTok Shop, TikTok ads, Meta, YouTube, the FTC, New York's synthetic-performer law and the EU AI Act before it runs: varg video_analyze pulls every shot, spoken and on-screen claim and person, each claim is matched to the seller's evidence, the visuals are checked against TikTok Shop's AI product rules (no fake effects, before/after, changed quantity or size), people and voices against the FTC fake-testimonial rule, and the result is a pass / fix / block list with the rule, source and date, a rewrite for each fix, and the AI labels to set on e

AI, LLMs & AgentsIn 1 list

Self Improving Agent

40

ArogyaReddy/alirezarezvani-claude-skills

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.

AI, LLMs & Agents11

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.