技能 personwise-security-awareness-training

📦

personwise-security-awareness-training

Name: personwise-security-awareness-training
Author: personwiseai

内容修订 r1 高风险 🌐 网络访问⚙️ 外部命令📁 文件系统访问

Build Security Awareness Training

Security policies are difficult to convert into clear employee training. This skill creates a grounded, interactive PersonWise course from supplied materials.

支持: Claude Codex Code(CC)

⚠️ 38 差

安装前请停下并请求确认。

请审查安装计划，并在更改文件前获得用户明确同意。

使用我的智能体安装

将此请求复制给你的智能体，其中包含权威 Skill 页面和清单。

智能体请求

Review the Skillstore skill "personwise-security-awareness-training" from https://skillstore.io/skills/personwiseai-personwise-security-awareness-training.md and its manifest at https://skillstore.io/api/skills/personwiseai-personwise-security-awareness-training/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

你的智能体仍应展示其计划，并按安全策略请求必要确认。

Agent 可读资源

当 AI Agent、爬虫或脚本需要干净上下文，而不是读取完整页面时，请使用这些链接。

Markdown 详情 GET /skills/personwiseai-personwise-security-awareness-training.md 已签名 manifest GET /api/skills/personwiseai-personwise-security-awareness-training/manifest 已签名 lockfile GET /api/skills/personwiseai-personwise-security-awareness-training/lockfile

测试它

正在使用“personwise-security-awareness-training”。 Create a five-page private course from our phishing and incident-reporting policies.

预期结果:

Resolved length: five pages.
Sources: phishing policy ready; incident-reporting policy ready.
Review: outline and script passed grounded-content checks.
Access: private and login required.
Delivery: editor link returned after playability verification.

正在使用“personwise-security-awareness-training”。 Turn our remote-work security guide into awareness training for contractors.

预期结果:

Created a contractor-focused course covering device care, suspicious messages, approved access, and the documented reporting path. The course remains private.

正在使用“personwise-security-awareness-training”。 Publish the reviewed course for anyone with the link and report its final status.

预期结果:

The course completed successfully, link access is enabled, and the returned share link is ready for distribution.

安全审计

高风险

v1 • 2026/8/5 打开版本化报告

Two static network findings are confirmed because the bootstrap installs opaque vendor executables that this audit cannot inspect. The remaining 140 static matches are false positives involving Markdown formatting, defensive installer operations, or signed descriptor data. Semantic review also found unvalidated service-supplied command execution and sensitive-document upload risks.

已扫描文件

648

分析行数

复核项

已忽略误报

已确认安全问题 (2)

高

SKILL.md:107-115

Unvalidated Service-Supplied Command Execution

The skill tells the agent to run the exact update action returned by the PersonWise service after approval. Without an argv allowlist, a compromised response could supply an arbitrary shell command.

The instruction to execute the returned action exactly is explicit, while no command grammar or metacharacter rejection is defined.

中

SKILL.md:197-205

External Upload of Potentially Sensitive Policies

The workflow uploads every user-selected source document to PersonWise. Security policies and incident procedures can contain sensitive internal information, so this creates a material data-egress boundary.

The source-add workflow and upload language directly confirm remote transmission; user selection limits scope but does not remove confidentiality risk.

能力复核项 (2)

这些是真实的本地能力，对此技能可能是预期行为，因此需要复核，但不会按已确认恶意行为计分。

高

assets/bootstrap.ps1:43

Hardcoded URL

$request = [Net.Http.HttpRequestMessage]::new([Net.Http.HttpMethod]::Get, "https://releases.personwi

The installer downloads and installs an unaudited executable from the author's server. TLS, fixed size, and a pinned hash verify delivery but not binary safety.

高

assets/bootstrap.sh:132

Hardcoded URL

url="https://releases.personwise.ai/cli/v1.1.6/$artifact"

The installer downloads and installs an unaudited executable from the author's server. Restricted TLS and pinned hashes protect integrity but do not establish benign behavior.

风险因素

🌐 网络访问 (2)

assets/bootstrap.ps1:43 assets/bootstrap.sh:132

⚙️ 外部命令 (50)

📁 文件系统访问 (7)

assets/bootstrap.sh:81 assets/bootstrap.sh:83 assets/bootstrap.sh:128 assets/bootstrap.sh:16 assets/bootstrap.sh:18 assets/bootstrap.sh:128 assets/bootstrap.sh:180

审计者: codex

分享与引用此报告

分享版本化评估报告、中性徽章、嵌入卡片和引用。Skillstore 只报告证据，不判断该 Skill 是否安全。

打开版本化报告

复制报告链接

https://skillstore.io/skills/personwiseai-personwise-security-awareness-training/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/personwiseai-personwise-security-awareness-training/security.svg)](https://skillstore.io/skills/personwiseai-personwise-security-awareness-training?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/personwiseai-personwise-security-awareness-training?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/personwiseai-personwise-security-awareness-training/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/personwiseai-personwise-security-awareness-training.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

学术引用 (APA · BibTeX · CFF)

APA 引用

personwiseai. (2026). personwise-security-awareness-training security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/personwiseai-personwise-security-awareness-training/audits/1

BibTeX 引用

@techreport{personwiseai-personwiseai-personwise-security-awareness-training-2026,
  author = {personwiseai},
  title = {personwise-security-awareness-training security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/personwiseai-personwise-security-awareness-training/audits/1},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "personwise-security-awareness-training security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "personwiseai"
date-released: "2026-08-05"
url: "https://skillstore.io/skills/personwiseai-personwise-security-awareness-training/audits/1"
identifiers:
  - type: other
    value: "skillstore:personwiseai-personwise-security-awareness-training:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore 评分

评分依据证据置信度: 中

架构

可维护性

内容

社区

规范符合性

你能构建什么

Train New Employees

Convert approved security policies into a concise private course covering recognition, response, and reporting.

Refresh Department Guidance

Create role-specific awareness training from current procedures for teams facing distinct security risks.

Publish Compliance Support

Prepare a reviewed awareness course for controlled internal sharing without claiming external certification.

试试这些提示

Create a Basic Course

Build a private security awareness course from [policy file] for [audience]. Focus on recognizing threats and using the documented reporting channel.

Set Course Scope

Create a [page count]-page security awareness course from [materials]. Cover [topics], use [language], and keep every factual claim grounded.

Use Materials Only

Create a materials-only course from [documents] for [audience]. Include recognition, response, reporting, and a short understanding check.

Review and Publish

Resume course [project identifier], verify every source and checkpoint, correct unsupported content, then publish with [private or link] access.

最佳实践

Provide current, approved policies and identify the intended learner audience.
Specify the desired access mode, page count, language, and required reporting channel.
Review sensitive documents before authorizing their upload to PersonWise.

避免

Do not request invented breach stories, threat statistics, policies, or reporting procedures.
Do not present course completion as security certification or proof of practical competence.
Do not upload unrelated files, secrets, credentials, or documents without clear authorization.