Developers Are Installing AI Agent Skills Too Fast

May 25, 2026

235,000 installs per week.

That’s how quickly developers are downloading AI agent skills — packages that give AI coding agents new capabilities like shell access, file system operations, cloud access, and deployment permissions.

But unlike traditional npm packages, agent skills introduce a completely new security problem: natural language instructions that AI agents can interpret and execute autonomously.

In this video, we break down:

  • What AI agent skills actually are
  • Why they create a new attack surface
  • How prompt injection changes software security
  • The findings from Snyk’s scan of nearly 4,000 agent skills
  • Why traditional static analysis tools fail here
  • How to scan your own AI agent setup for vulnerabilities

We also look at the open-source Agent Scan tool, the Snyk + Vercel integration, and practical steps developers can take today to secure their AI coding environments.

Use Snyk for free to find and fix security issues in your applications today! https://snyk.co/ugLYn

✍️ Resources ✍️

⏲️ Chapters ⏲️

0:00 AI Agent Skills Are Exploding in Popularity

0:56 What Agent Skills Are and How They Work

1:38 Why Agent Skills Create a New Security Threat Model

3:30 Snyk’s Scan of Nearly 4,000 AI Agent Skills

4:41 How Snyk and Vercel Built Automated Security Scanning

5:44 How to Scan Your Own AI Agent Environment

6:24 The 3 Biggest Takeaways About Agent Skill Security

7:02 Final Thoughts and Community Discussion

⚒️ About Snyk ⚒️

Snyk helps you find and fix vulnerabilities in your code, open-source dependencies, containers, infrastructure-as-code, software pipelines, IDEs, and more! Move fast, stay secure.

Learn more about Snyk: https://snyk.co/ugLYl

📱 Connect with Us 📱

🖥️ Website: https://snyk.co/ugLYl
🐦 X: http://twitter.com/snyksec
💼 LinkedIn: https://www.linkedin.com/company/snyk
💬 Discord: https://discord.gg/devsecops-community-918181751526948884

🔗 Hashtags 🔗
#shaihulud #aisecurity #aiagents