Habilidades personwise-partner-training

📦

personwise-partner-training

Name: personwise-partner-training
Author: personwiseai

Revisión del contenido r1 Riesgo alto 🌐 Acceso a red⚙️ Comandos externos📁 Acceso al sistema de archivos

Build Grounded Partner Training Courses

Partner teams need consistent onboarding without unsupported commercial claims. This skill builds a source-grounded, interactive PersonWise course with review checkpoints, access controls, and learner questions.

Compatible con: Claude Codex Code(CC)

⚠️ 38 Deficiente

Detente y solicita confirmación antes de instalar.

Revisa el plan y obtén el consentimiento explícito del usuario antes de modificar archivos.

Instalar con mi Agente

Copia esta solicitud en tu Agente. Incluye la página canónica del Skill y el manifiesto.

Solicitud de agente

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

Tu Agente debe seguir mostrando su plan y solicitar cualquier confirmación exigida por la política de seguridad.

Recursos legibles por agentes

Usa estos enlaces cuando un agente de IA, crawler o script necesite contexto limpio en vez de leer la página completa.

Detalle Markdown GET /skills/personwiseai-personwise-partner-training.md Manifest firmado GET /api/skills/personwiseai-personwise-partner-training/manifest Lockfile firmado GET /api/skills/personwiseai-personwise-partner-training/lockfile

Pruébalo

Usando "personwise-partner-training". Create a five-page private onboarding course from our partner handbook.

Resultado esperado:

Resolved format: five-page private partner onboarding course.
Teaching arc: partnership, product story, deal flow, approved claims, and escalation.
Evidence: supplied handbook only, with unsupported commercial questions routed to the partner team.

Usando "personwise-partner-training". Turn our reseller guide into training with a short knowledge check.

Resultado esperado:

Course structure: reseller value, customer narrative, handoff process, branding limits, and support contacts.
Knowledge check: scenario questions based only on approved guide content.
Delivery: interactive presenter with source-grounded learner questions.

Usando "personwise-partner-training". Update the existing course and give partners a shareable link.

Resultado esperado:

The course was reviewed against current sources, updated at supported fields, published with link access, and checked for playability.

Auditoría de seguridad

Riesgo alto

v1 • 5/8/2026 Abrir el informe versionado

Two hardcoded release URLs are confirmed network and software supply-chain risks, while shell substitutions, Markdown backticks, installer safeguards, and signed descriptor entropy are false positives. Semantic review found third-party executable installation, server-supplied update commands, external document uploads, and implicit course-credit consumption.

Archivos escaneados

647

Líneas analizadas

Elementos de revisión

Falsos positivos ignorados

Preocupaciones de seguridad confirmadas (4)

Alto

SKILL.md:71-77 assets/bootstrap.sh:132-165 assets/bootstrap.ps1:43-84

Third-Party Executable Installation and Execution

The workflow installs a closed PersonWise executable into a user executable directory and then uses it for authenticated operations. Hash pinning limits tampering, but reviewers cannot inspect the downloaded binary in this skill package.

The instructions and both installers directly show downloading, verifying, installing, and later invoking the external PersonWise executable.

Alto

SKILL.md:106-126

Externally Supplied Update Command Execution

The skill tells the agent to execute an exact update command returned by the PersonWise service. A compromised response could influence local command execution despite the required user approval.

The prose explicitly requires running the returned action command without substitution and provides fallback installation commands.

Medio

SKILL.md:196-204

External Upload of Partner Materials

The workflow uploads user-selected partner documents to PersonWise and treats selection as upload authorization. Sensitive commercial materials may leave the local environment without a separate destination disclosure.

The source add command and surrounding instructions explicitly direct local files to the external PersonWise workflow.

Medio

SKILL.md:129-135

Implicit Consumption of Existing Course Credits

A general course-creation request is treated as authorization to consume existing course credits. The skill forbids a separate confirmation before this billable or limited account resource is used.

The authorization section explicitly states that creation consumes required credits without asking again.

Elementos de revisión de capacidades (2)

Estas son capacidades locales reales que pueden esperarse para esta habilidad, por lo que requieren revisión, pero no se cuentan como comportamiento malicioso confirmado.

Bajo

assets/bootstrap.ps1:43

Hardcoded URL

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

The installer downloads a versioned PersonWise executable archive from an external release server at assets/bootstrap.ps1:43. Pinned size and SHA-256 checks reduce tampering risk, but the network and software supply-chain action is real.

Bajo

assets/bootstrap.sh:132

Hardcoded URL

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

The installer downloads a versioned PersonWise executable archive from an external release server at assets/bootstrap.sh:132. Pinned size and SHA-256 checks reduce tampering risk, but the network and software supply-chain action is real.

Factores de riesgo

🌐 Acceso a red (2)

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

⚙️ Comandos externos (50)

📁 Acceso al sistema de archivos (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

Auditado por: codex

Compartir y citar este informe

Comparte el informe de evaluación versionado, la insignia neutral, la tarjeta insertable y las citas. Skillstore presenta evidencias sin decidir si este Skill es seguro.

Abrir el informe versionado

Copiar enlace del informe

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

Insignia Markdown

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

Insignia HTML

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

Tarjeta para insertar

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

Citas académicas (APA · BibTeX · CFF)

Cita APA

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

Cita BibTeX

@techreport{personwiseai-personwiseai-personwise-partner-training-2026,
  author = {personwiseai},
  title = {personwise-partner-training security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/personwiseai-personwise-partner-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-partner-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-partner-training/audits/1"
identifiers:
  - type: other
    value: "skillstore:personwiseai-personwise-partner-training:audit:1"
    description: "Skillstore immutable audit report identifier"

Puntuación de Skillstore

Por qué esta puntuación Confianza de la evidencia: Medio

Arquitectura

Mantenibilidad

Contenido

Comunidad

Cumplimiento de la especificación

Lo que puedes crear

Onboard new channel partners

Turn approved program documents into a private course covering product messaging, deal registration, handoffs, branding rules, and escalation contacts.

Train reseller teams

Create a concise reseller course with approved customer narratives, self-check questions, and clear boundaries for commercial claims.

Publish a controlled program update

Revise an existing course from current materials, review every checkpoint, and release it with the requested access mode.

Prueba estos prompts

Create a basic partner course

Create a private partner training course from [materials]. Teach [audience] the product story, deal flow, approved claims, and escalation path.

Ground a course in documents

Build a [page count]-page partner onboarding course using only [documents]. Preserve approved terminology and route unsupported commercial questions to [partner team].

Add assessment and visual direction

Create a private reseller course from [materials] for [audience]. Include [assessment type], conceptual deal-flow visuals, and an interactive presenter brief.

Review and publish an existing course

Resume course [project ID]. Verify every source is ready, review outline and script checkpoints, correct unsupported claims, then publish with [access mode].

Mejores prácticas

Provide current, approved partner materials and identify the factual authority for commercial claims.
Specify the audience, desired page count, assessment needs, language, and access mode before creation.
Review each outline, script, and image checkpoint before advancing or publishing.

Evitar

Do not invent commissions, margins, territories, lead flows, legal status, earnings, portals, or tier structures.
Do not upload agent-discovered files or images without explicit approval.
Do not call private editor links shareable or describe Topics submissions as approved.