Protect AI Harnesses with HOL Guard
Local AI harnesses can expose risky tools, plugins, and configuration changes. HOL Guard guides controlled setup, approval review, evidence collection, and package verification.
このリクエストをエージェントにコピーしてください。正規の Skill ページとマニフェストが含まれています。
Review the Skillstore skill "hol-guard" from https://skillstore.io/skills/hashgraph-online-hol-guard.md and its manifest at https://skillstore.io/api/skills/hashgraph-online-hol-guard/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.エージェントは引き続き計画を提示し、セキュリティポリシーで必要な確認を求める必要があります。
AI エージェント、クローラー、スクリプトがページ全体ではなく整理されたコンテキストを必要とする場合は、これらのリンクを使ってください。
「hol-guard」を使用しています。 Check whether this Codex workspace is protected.
期待される結果:
HOL Guard detected the Codex workspace. Protection is not confirmed because the status check did not prove an active Guard installation.
「hol-guard」を使用しています。 Review the pending Guard approval before I decide.
期待される結果:
The request remains pending. The review identifies its requested scope, risk reason, related configuration difference, and available receipt evidence.
「hol-guard」を使用しています。 Verify this skill package for release.
期待される結果:
Package verification completed with one unresolved scanner failure. Release readiness is not confirmed until that failure is inspected and resolved.
Most static matches are false positives caused by Markdown backticks, command fences, and a rule prohibiting .env access. Confirmed findings involve package installation, harness configuration, approval actions, and optional cloud synchronization; these are legitimate features with operational security risk.
これらは、このスキルに期待される可能性のある実際のローカル機能であるため、レビューが必要ですが、確認済みの悪意ある動作としてはカウントされません。
バージョン付き評価レポート、中立的なバッジ、埋め込みカード、引用を共有できます。Skillstore は証拠を報告しますが、この Skill が安全かどうかは判断しません。
https://skillstore.io/skills/hashgraph-online-hol-guard/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/hashgraph-online-hol-guard?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/hashgraph-online-hol-guard?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/hashgraph-online-hol-guard/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/hashgraph-online-hol-guard.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>hashgraph-online. (2026). hol-guard security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/hashgraph-online-hol-guard/audits/1@techreport{hashgraph-online-hashgraph-online-hol-guard-2026,
author = {hashgraph-online},
title = {hol-guard security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/hashgraph-online-hol-guard/audits/1},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "hol-guard security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "hashgraph-online"
date-released: "2026-08-27"
url: "https://skillstore.io/skills/hashgraph-online-hol-guard/audits/1"
identifiers:
- type: other
value: "skillstore:hashgraph-online-hol-guard:audit:1"
description: "Skillstore immutable audit report identifier"
Install Guard integration, run a dry check, and verify protection for Codex, Claude Code, or another supported harness.
Inspect queued approvals, risk reasons, receipts, and configuration differences before deciding whether work may continue.
Lint and verify plugins, skills, MCP servers, or marketplace packages before publishing a release.
Check whether HOL Guard and plugin-scanner are installed. Report availability and recommend isolated installation steps without changing my environment.
Protect my [harness] workspace with HOL Guard. Run a dry check first, explain planned changes, and verify final status with command evidence.
Inspect Guard request [request-id]. Explain its risk reason and scope, show relevant evidence, and wait for my decision before approving or denying.
Audit this mixed agent workspace. Verify packages, inspect Guard status and evidence, then identify unresolved release risks without claiming readiness prematurely.
作成者
hashgraph-onlineライセンス
Apache-2.0
Skillstore リビジョン
r1
バージョンに関する注意
作者はバージョンを宣言していません。
参照
40175672d649fa6482bff53a7acf4ecdd6a04a96
メンテナンスの新しさ
2026/8/27
利用状況
1 ダウンロード · 0 閲覧
ファイル構成
📄 SKILL.md
Scan AI Plugins Before Installation
Unreviewed agent extensions can contain prompt injection, unsafe commands, secret exposure, or supply-chain risks. This skill guides local scanning and clear interpretation before trust.
Discover and Connect With Registered AI Agents
Finding compatible agents across separate registries is difficult. This skill searches a unified registry and supports authenticated messaging, registration, and skill publishing.
Verify Release Health After Deployment
作成者 logbrewco
Release decisions can be difficult when error counts and traffic change together. Compare release evidence and receive a Go, Rollback, or Wait recommendation.
Audit Software Releases with Evidence
作成者 glenskii
Release decisions often rely on incomplete evidence and inconsistent standards. This skill applies structured controls, deterministic scoring, and mandatory gates to assess readiness.
Audit Python Web Apps Before Release
作成者 glenskii
Python teams need repeatable checks for common application security controls. This skill provides configurable pytest coverage with clear evidence, boundaries, and release decisions.
医療機器リスクファイルの管理
作成者 alirezarezvani
医療機器チームには、設計、規制対応、市販後業務にわたって一貫したリスクマネジメントのエビデンスが必要です。このスキルは、ISO 14971 に基づく計画、分析、管理策、ファイル保守を支援します。
ISO 27001セキュリティガバナンスの実装
作成者 davila7
HealthcareおよびMedTechチームには、リスク、管理策、インシデント、監査を結び付ける体系的なISO 27001セキュリティプログラムが必要です。このスキルは、ISO 27001およびISO 27002を使用して、ISMS計画、リスクアセスメント、管理策の選定、認証準備を支援します。
ISO 27001 ISMS 統制の監査
作成者 alirezarezvani
ISMS 監査には、明確な範囲、証拠、リスクベースの優先順位が必要です。このスキルは、ISO 27001 監査計画、統制テスト、準備作業を支援します。