snykOfficial·17 Agent Skills Included

agent-scan

Scan AI agents, MCP servers, and skills for hidden security threats

Discovers installed AI agents, MCP servers, and skills on your machine and scans them for prompt injections, malware payloads, and leaked secrets. Eliminates the risk of running untrusted agent components blindly by flagging dangerous commands, credential handling, and suspicious downloads before execution. Works across Claude Code, Cursor, Windsurf, Gemini CLI, and other popular agents on macOS, Linux, and Windows.

2,893|257

↗

npx skills add snyk/agent-scan --all -g -y

All Skills in This Repository (17)

Pure Emerald Level Indicators

📦 In Repo

snyk

test-skill

Load and process a basic skill unit to verify the execution environment.

theme-factory

Apply pre-designed or custom-generated themes to slides, documents, and HTML pages.

doc-coauthoring

Guide structured co-authoring of technical specs, proposals, and decision docs.

xlsx

Create and edit Excel spreadsheets with formulas and pandas analysis.

pdf

Extract text and structured data from PDF documents using pypdf and pdfplumber.

algorithmic-art

Generate p5.js algorithmic art with seeded randomness and interactive parameters.

internal-comms

Generate internal company communications using templates for updates, newsletters, and FAQs.

skill-creator

Guide developers through creating and structuring AI skills with SKILL.md.

canvas-design

Generate original visual art and design philosophies in PNG and PDF formats.

pptx

Automates creation, editing, and analysis of PowerPoint .pptx presentations via OOXML manipulation and HTML-to-PPTX conversion.

slack-gif-creator

Generates Slack-optimized animated GIFs with custom animations, frame composition, and color quantization.

webapp-testing

Test local web applications with Playwright scripts and capture screenshots.

Official

Intermediate

Frequently Asked Questions

FAQPage Schema

How to install Agent Scan?▼

Run `npx skills add snyk/agent-scan --all -g -y` in your terminal to install all tools in this suite globally.

What does Agent Scan detect?▼

It detects over 15 security risks including prompt injection, tool poisoning, malicious code, hardcoded secrets, and insecure credential handling in MCP servers and agent skills.

Which AI agents does Agent Scan support?▼

It auto-discovers configurations for Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Gemini CLI, OpenClaw, Kiro, Codex, Amazon Q, and more across macOS, Linux, and Windows.

Is it safe to scan unknown MCP configurations?▼

Scanning starts the MCP servers defined in a config, so you should run scans inside a sandbox or Docker container when evaluating untrusted third-party configurations.

Do I need a Snyk account to use Agent Scan?▼

Yes. You need a free Snyk API token from app.snyk.io, which you set as the SNYK_TOKEN environment variable before running any scan.