Skip to content
Back to skills

Guard

ASecurity

Use HOL Guard to preview and protect AI-agent package installs, Cursor surfaces, CI, and automation workflows.

  • 791 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added August 31, 2026
ai-agentsrust

Works with

  • cursor
  • cli
  • mcp

Security analysis

A92/100
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro scans all 20 files and shows the line behind each finding

Scanned September 29, 2026

npx -y skills add hashgraph-online/hol-guard --skill guard --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Guard?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Guard
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hashgraph-online-guard/badge)](https://www.skillsdirectory.com/skills/hashgraph-online-guard)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: hol-guard-protection
description: Use HOL Guard to preview and protect AI-agent package installs, Cursor surfaces, CI, and automation workflows.
---

# HOL Guard Skill Guidance

Use this guidance when an AI agent is about to add or update dependencies.

## Before package installs

1. Preview the install decision:
   - `hol-guard protect --dry-run -- npm install <package>`
2. Check current workspace risk posture:
   - `hol-guard supply-chain scan --json`
3. Explain a specific package verdict:
   - `hol-guard supply-chain explain <package>@<version> --ecosystem <ecosystem>`
4. Confirm package manager interception is installed:
   - `hol-guard package-shims status --json`
5. Repair a missing or tampered package manager shim:
   - `hol-guard package-shims repair --manager npm --json`

## Cursor editor and Cursor CLI

Cursor has two protection surfaces. **Cursor editor** covers MCP servers in `.cursor/mcp.json`. **Cursor CLI** covers the `cursor-agent` command path. Keep them distinct when activating, checking, repairing, or removing Guard.

1. Connect Cursor editor protection:
   - `hol-guard apps connect cursor --surface editor`
2. Connect Cursor CLI protection:
   - `hol-guard apps connect cursor --surface cli`
3. Test a Cursor surface without changing config:
   - `hol-guard apps test cursor --surface editor`
   - `hol-guard apps test cursor --surface cli`
4. Repair only the stale surface named by Guard Cloud:
   - `hol-guard apps repair cursor --surface editor`
   - `hol-guard apps repair cursor --surface cli`
5. Remove protection only after confirmation:
   - `hol-guard apps disconnect cursor --surface editor --confirm disconnect-cursor`
   - `hol-guard apps disconnect cursor --surface cli --confirm disconnect-cursor`

Guard owns trust checks, drift repair, redacted receipts, and Cloud sync. Cursor owns its native editor and CLI behavior. If a surface is missing, unsupported, or unavailable, report that state instead of inventing an install URL or fallback command.

## During CI and automation

- Route dependency installs through Guard:
  - `hol-guard protect -- npm ci`
- Use workspace audits before release:
  - `hol-guard supply-chain audit --json`

## If Guard blocks a package

- Review the blocking reason and suggested fix version.
- Prefer upgrading to a safe version.
- If it is a verified false positive, use a scoped and expiring exception with recorded reason.

Files in this skill

  • SKILL.md2.2 KB
  • adr/0001-mdm-managed-install-contract.md2.1 KB
  • adr/0002-self-protection-authority.md2.8 KB
  • adr/0003-desktop-shell-and-tray-ownership.md4.7 KB
  • adr/0004-extension-control-center-semantics.md5.7 KB
  • adr/0005-protection-center-semantics.md3.8 KB
  • adr/0006-native-rust-runtime-boundary.md2.1 KB
  • adr/0007-native-runtime-packaging.md2.3 KB
  • adr/0008-native-resident-protocol-and-admission.md3 KB
  • adr/0009-native-and-daemon-critical-failure.md2.6 KB
  • adr/0010-native-posttool-default-auto.md2.1 KB
  • adr/0011-extension-first-managed-controls.md6.5 KB
  • all-harness-hook-review.md6.3 KB
  • architecture.md3.8 KB
  • cline-local-protection-contract.md5.8 KB
  • cline-security-closure.md6.1 KB
  • cline-upstream-evidence.md3 KB
  • cloud-command-capability.md3.3 KB
  • command-activity-dashboard-ia.md3.7 KB
  • command-activity-privacy.md5.2 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.