invariantlabs-aiOfficial·17 Agent Skills Included

mcp-scan

Scan AI agents, MCP servers, and skills for security risks

Discovers installed AI agents, MCP servers, and skills on your machine and scans them for prompt injections, malware payloads, and leaked secrets. Eliminates the manual work of auditing agent configurations across Claude, Cursor, VS Code, Windsurf, and other tools. Flags risky tool descriptions, hardcoded credentials, and suspicious downloads so you can fix issues before they reach production.

2,893|257

↗

npx skills add invariantlabs-ai/mcp-scan --all -g -y

All Skills in This Repository (17)

Pure Emerald Level Indicators

📦 In Repo

invariantlabs-ai

test-skill

Parse SKILL.md YAML frontmatter to validate required name and description fields.

theme-factory

Apply cohesive visual themes from themes/*.md to slides, documents, and reports.

doc-coauthoring

Guide structured three-stage documentation workflows for proposals and technical specs.

xlsx

Create, edit, and analyze Excel workbooks with formula preservation and recalculation.

pdf

Processes PDFs with extraction and manipulation workflows.

algorithmic-art

Generate philosophy-driven generative art with seeded p5.js in self-contained HTML.

internal-comms

Generate internal communications using guideline files from the examples directory.

skill-creator

Create and validate Skill Units with SKILL.md frontmatter and .skill packaging.

canvas-design

Generate a one-page canvas PDF or PNG from a visual design philosophy.

pptx

Create, edit, and analyze PPTX files through a scripted interface.

slack-gif-creator

Build, optimize, and validate Slack-compatible animated GIFs from programmatically generated frames.

webapp-testing

Automate Playwright-based UI testing for local web applications with Python 3.x and server helper scripts.

Official

Intermediate

Frequently Asked Questions

FAQPage Schema

How to install mcp-scan?▼

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

What does mcp-scan detect?▼

It detects prompt injections, tool poisoning, malicious code, hardcoded secrets, and insecure credential handling in MCP servers and agent skills.

Which AI agents does mcp-scan support?▼

It auto-discovers configurations for Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Gemini CLI, and several other agents on macOS, Linux, and Windows.

Is it safe to scan unknown MCP servers?▼

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

Can I scan a single skill file?▼

Yes. Point the scanner at any SKILL.md file or skills directory to audit just that skill for hidden threats.