Product

Snyk Agent Scan

by Snyk

Product website
https://github.com/snyk/agent-scan
Categories
Developer Tools LLM Security & Guardrails

Description

An open-source security scanner for AI agents, MCP servers, and agent skills that auto-discovers local agent configs, connects to MCP servers to fetch tool descriptions, and scans for risks including prompt injection, tool poisoning, and hardcoded secrets.

AI-native score

How ready this product is for agents to use, on a 0–100 scale across four weighted dimensions. Security is one of them, so a high score is not a substitute for your own security or vendor-risk review. How is this scored?

Unrated. Only 38% of the scored decision fields are researched, so the grade is held until more are confirmed. The breakdown below shows what's been scored.

Integration3/10Trust1/6Portability4/4Security0/4Tier C36/100
Component Raw Weight Contribution
Integration 3/10 35% 10.5
Trust 1/6 30% 5.0
Portability 4/4 20% 20.0
Security 0/4 15% 0.0
Signals that fired
  • Integration: Command-line interface (+1) ; SDK / developer kit (+1) ; Agent skill (+1)
  • Trust: Verified trust center (+1)
  • Portability: Open standards (+1) ; No proprietary-SDK lock-in (+1) ; Self-hostable (+1) ; Open source (+1)
Signals not researched

These gaps cover the fields used in the AI-native score.

  • Integration surfaces: llms.txt, Headless signup, MCP servers, Native connectors, API specs
  • Trust & data policy: Multi-factor authentication, Zero data retention, No generative AI training, Hard budget caps, Sandbox environment, Data export, Data import, Standard protocol access, Documented provider swap
  • Security & compliance: Compliance certifications, Access controls

Trust & data policy

Trust center
Vendor trust center
Open standards
Yes
No proprietary-SDK lock-in
Yes
Self-hostable
Yes
Open source
Yes
Source code
https://github.com/snyk/agent-scan

Not yet researched Multi-factor authentication, Zero data retention, No generative AI training, Hard budget caps, Sandbox environment, Data export, Data import, Standard protocol access, Documented provider swap

What it does

Capabilities

  • Agent and MCP Security Scanning

    Scan AI agents, MCP servers, and agent skills for risks such as prompt injection, tool poisoning, and hardcoded secrets.

    View 1 product

Jobs to be done

  • Protect AI applications from security threats

    Detect or block malicious instructions, unsafe tool use, or sensitive data exposure in AI applications.

    View 3 products
  • Scan AI agents and MCP servers for security risks

    Detect prompt injection, tool poisoning, and credential-handling risks in agent configurations and MCP servers.

    View 1 product

Integration surfaces

How an agent connects to this product and finds its documentation. The largest dimension of the AI-native score (35%).

WebMCP
No

Command-line interfaces

Agent skills

Packaged skills an agent can load to operate this product.

Developer kits

Confirmed absent Agent2Agent (A2A) servers

Not yet researched llms.txt, Headless signup, MCP servers, Native connectors, API specs

Offers

No offers recorded.

Reviews

No approved reviews yet.

RSS: approved reviews

Catalog activity

Track how this entry changes as proposals are opened and merged.

RSS: merged changes · RSS: open proposals

Products from other publishers that share a job-to-be-done or category, most-shared first.

  • LiteLLM by LiteLLM Unrated

    Same job: Protect AI applications from security threats (not assessed)

  • Lakera Guard by Lakera Unrated

    Same job: Protect AI applications from security threats (not assessed)

  • Postmark by Postmark Tier B
    Developer Tools Email API / Transactional Email
  • Sentry by Sentry Tier B
    Developer Tools Error Monitoring
  • Speakeasy by Speakeasy Tier C
    Developer Tools
  • Mailgun by Mailgun Tier C
    Developer Tools Email API / Transactional Email

Own this product? Add a directory badge to your site

Link your site back to this Open Agent Guide listing. The badge makes no grade claim while this product is unrated, and updates on its own once enough is verified to assign a grade.

Snyk Agent Scan — listed on Open Agent Guide Snyk Agent Scan — listed on Open Agent Guide

HTML

<a href="https://www.openagentguide.com/organizations/snyk/products/snyk-agent-scan/?utm_source=badge&amp;utm_medium=referral">
  <img src="https://www.openagentguide.com/organizations/snyk/products/snyk-agent-scan/badge.svg" alt="Snyk Agent Scan — listed on Open Agent Guide" height="64" />
</a>

Markdown

[![Snyk Agent Scan — listed on Open Agent Guide](https://www.openagentguide.com/organizations/snyk/products/snyk-agent-scan/badge.svg?style=flat)](https://www.openagentguide.com/organizations/snyk/products/snyk-agent-scan/?utm_source=badge&utm_medium=referral)

The badge shows only that this product is listed; it makes no grade claim and can’t be self-set. How scoring works

Ready to decide?

Unrated · 38% researched. Grade withheld until more fields are verified.

Visit Snyk Agent Scan