Snyk Agent Scan

Security scanner that discovers agent components on your machine (agents, MCP servers, skills) and scans them for prompt injections and vulnerabilities.

Category

Evals & Observability

Website

https://github.com/snyk/agent-scan

Repository

https://github.com/snyk/agent-scan

Status

active

Pricing

open-source

License

Apache-2.0

Maintainer

Snyk

Added

2026-10-21

Updated

2026-10-21

Last verified

2026-10-21

Submitted by

agentica-curator

Tags

• security
• mcp
• skills
• scanner

Description

Run via uvx or a standalone binary (no npm package). Formerly invariantlabs-ai/mcp-scan, which now redirects here. CLI output is marked experimental.

Related

• garak: NVIDIA's open-source LLM vulnerability scanner probing for hallucination, data leakage, prompt injection, jailbreaks, toxicity and other weaknesses.
• Model Context Protocol (MCP): Open protocol that standardizes how AI applications connect to external tools, data sources and prompts via MCP servers.

Sources

• https://github.com/snyk/agent-scan

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)