Log in

Scan AI Agent Tools for Malware Before Installation

Patrick Illian Germany
3 comments

Apps it uses

AI agents such as Claude Code, Codex, and Gemini can install skills, plugins, and CLI tools in seconds. That is convenient, but each add-on runs with access to files, passwords, and accounts. A malicious add-on could steal API keys, read private data, or quietly take control of the agent.

I use `agent-guard` to make “check first, install after” the default. Before installation, it examines AI agent skills, MCP servers, and CLI tools for malware, prompt injection, and credential theft using professional, open-source security scanners from NVIDIA, Cisco, Datadog, and the Open Source Security Foundation.

The tool returns a clear verdict: safe to install or blocked, with the exact reason. It then installs only the verified version, preventing a different version from being swapped in between. A single check can also cover multiple AI agents, installing the approved add-on into every agent on the machine.

Free and open source: https://github.com/elliottwaves-20/agent-guard

Step-by-step

  1. I select the AI agent skill, MCP server, or CLI tool I want to install.
  2. I run `agent-guard` to scan it for malware, prompt injection, and credential theft.
  3. I review the verdict and the reason if the add-on is blocked.
  4. I install the exact version that was checked rather than an unverified replacement.
  5. If I use several AI agents, I install the approved add-on into all of them at once.
Industry
Software & Technology

3 comments

Have a question about this workflow, or a way to improve it?

Log in to comment Create a free account
Patrick Illian

I'm going to improve the system even further. Currently, only initial installations are checked here. However, the goal should be for updates to also be verified by Guard. This is currently in development. The goal is to provide even less experienced AI users with a system that, through multi-stage checks, keeps both the system and the Skills and MCPs up to date, avoids causing uncertainty due to false alarms (of which Nvidia’s SkillSpector, unfortunately, produces an extremely large number), and thus provides comprehensive protection without overwhelming the user (even the inexperienced one).

Posting guidelines