AgentScan HOL Guard

Related Products

  • Retool
    4.6 out of 5 stars 608 Ratings
    Visit Website for Retool
  • Jotform
    4.6 out of 5 stars 9,009 Ratings
    Visit Website for Jotform
  • Canditech
    5.0 out of 5 stars 111 Ratings
    Visit Website for Canditech
  • Gemini platform
    4.3 out of 5 stars 1,178 Ratings
    Visit Website for Gemini platform
  • LeaseAccounting.app
    Visit Website for LeaseAccounting.app
  • StackAI
    4.5 out of 5 stars 55 Ratings
    Visit Website for StackAI
  • Zendesk
    4.3 out of 5 stars 8,616 Ratings
    Visit Website for Zendesk
  • Google AI Studio
    4.8 out of 5 stars 42 Ratings
    Visit Website for Google AI Studio
  • SearchUnify
    4.5 out of 5 stars 150 Ratings
    Visit Website for SearchUnify
  • BAND
    5.0 out of 5 stars 3 Ratings
    Visit Website for BAND
AgentScan:

About

AgentScan is a free, deterministic security scanner for AI agent skills. It checks a skill directory (Claude Code, Codex, OpenCode, MCP servers) for prompt injection, secrets, network calls, malware patterns, and obfuscation before you install it. Every finding has file:line evidence and a confidence score. It never runs the skill, never uploads anything, and works offline. Free and open source (MIT); Trust Pack adds 90 pre-audited skills via one command.
HOL Guard:

About

HOL Guard is a local-first runtime security layer for AI agents that watches what an AI assistant is about to do and stops risky actions before they happen. It sits between the agent and the computer, evaluating supported tool calls and local artifacts for threats such as secret and credential exposure, destructive commands, prompt-injection-driven actions, malicious or changed packages, risky MCP configuration, and unsafe plugins, skills, hooks, and settings. Known threats can be blocked automatically, while ambiguous actions are paused for user approval so people remain in control. Guard runs entirely on the developer’s machine, works offline, and does not upload files, prompts, or passwords. Local checks typically complete in under 50 milliseconds and require no changes to existing code or routines. It supports coding agents including Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Hermes, and OpenClaw, with tailored integrations that inspect actions before execution.
AgentScan:

Platforms Supported

Windows Supported
Mac Supported
Linux Supported
Cloud Not Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported
HOL Guard:

Platforms Supported

Windows Supported
Mac Supported
Linux Supported
Cloud Not Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported
AgentScan:

Audience

Engineers and product builders who actively use AI agents for their end to end workflows.
HOL Guard:

Audience

Developers and engineering teams in need of a tool to prevent AI coding agents from exposing secrets, executing destructive commands, or performing other risky actions
AgentScan:

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported
HOL Guard:

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported
AgentScan:

API

Offers API Not Supported
HOL Guard:

API

Offers API Not Supported
AgentScan:

Screenshots and Videos

No images available
HOL Guard:

Screenshots and Videos

AgentScan:

Pricing

$59/year
Free Version Supported
Free Trial Not Supported
HOL Guard:

Pricing

$4.99 per month
Free Version Supported
Free Trial Not Supported
AgentScan:

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software
HOL Guard:

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software
AgentScan:

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported
HOL Guard:

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported
AgentScan:

Company Information

AgentScan
Founded: 2026
agentscan.baldbee.me/
HOL Guard:

Company Information

HOL
Founded: 2024
United States
hol.org/guard
AgentScan:

Alternatives

HOL Guard:

Alternatives

AgentScan:
HOL Guard:
AgentScan:
HOL Guard:
AgentScan:
antgrid

antgrid

Radha AI Products
HOL Guard:
nono

nono

Always Further
AgentScan:
HOL Guard:
AgentScan:

Categories

Agentic AI Supported
HOL Guard:

Categories

AI Security Supported
AgentScan:

Integrations

Claude Code Supported
Model Context Protocol (MCP) Supported
OpenAI Codex Supported
OpenCode Supported
Antigravity CLI Not Supported
Cursor Not Supported
Gemini CLI Not Supported
GitHub Not Supported
GitHub Copilot CLI Not Supported
Grok Not Supported
Hermes Agent Not Supported
Kimi Not Supported
OpenClaw Not Supported
Pi Agent Not Supported
Slack Not Supported
ZCode Not Supported
HOL Guard:

Integrations

Claude Code Supported
Model Context Protocol (MCP) Supported
OpenAI Codex Supported
OpenCode Supported
Antigravity CLI Supported
Cursor Supported
Gemini CLI Supported
GitHub Supported
GitHub Copilot CLI Supported
Grok Supported
Hermes Agent Supported
Kimi Supported
OpenClaw Supported
Pi Agent Supported
Slack Supported
ZCode Supported
AgentScan:
Claim AgentScan and update features and information
Claim AgentScan and update features and information
HOL Guard:
Claim HOL Guard and update features and information
Claim HOL Guard and update features and information