agent-scan

agent-scan

Security scanning tool for AI agents, MCP servers, and skills.

MCPDevOpen source
Type
MCP
Transport
stdio
Open source
Yes
GitHub Stars
★ 2.6k
Source
mcp-github

Overview

Snyk Agent Scan is a security tool designed to scan AI agents, MCP servers, and skills. It helps users discover and scan agent components on machines, detecting prompt injection and vulnerabilities. Supports automatic discovery of MCP configurations, agent tools, and skills, and identifies multiple security risks. Ideal for developers and teams needing to ensure the security of AI components. After installation via pip, scans can be run immediately.

Capabilities

  • Automatic discovery of MCP configurations, agent tools, and skills
  • Detection of prompt injection and vulnerabilities
  • Support for multiple agents and operating systems
  • Detection of 15+ types of security risks

Use cases

Scanning AI agents and skills to detect security risksPerforming security checks in development environmentsEnterprise-level security management

Setup

Requires: Python 环境pip
pip install snyk-agent-scan

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Is the CLI output stable?

CLI output is experimental and may change.

How can I skip skill scanning?

Use the `--no-skills` parameter to ignore skill scanning.

Related skills