📦

wan-2-7

Name: wan-2-7
Author: prime-skills

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

Generate Wan 2.7 Videos with RunComfy

Video requests require clear motion prompts and compatible model settings. This skill guides Wan 2.7 generation through RunComfy with optional audio-driven lip-sync.

Compatible con: Claude Codex Code(CC)

📊 69 Adecuado

Maintain this Skill? Claim it 📊 69 Adecuado

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 "wan-2-7" from https://skillstore.io/skills/prime-skills-wan-2-7.md and its manifest at https://skillstore.io/api/skills/prime-skills-wan-2-7/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

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/prime-skills-wan-2-7.md Manifest firmado GET /api/skills/prime-skills-wan-2-7/manifest Lockfile firmado GET /api/skills/prime-skills-wan-2-7/lockfile

Pruébalo

Usando "wan-2-7". Prepare a five-second 1080p widescreen showcase for a desk lamp.

Resultado esperado:

Prepared request: Wan 2.7 text-to-video, five seconds, 1080p, 16:9.
Visual prompt: A desk lamp on a clean studio surface, soft lighting, and a slow camera push-in.
No generation has been run in this example.

Usando "wan-2-7". Plan a vertical spokesperson clip with my approved 12-second MP3 voiceover.

Resultado esperado:

Prepared request: 12 seconds, 9:16, with the supplied audio URL for lip-sync.
Visual prompt: Medium close-up of a spokesperson, locked tripod, warm side lighting, and subtle breathing motion.
Confirm the MP3 is no larger than 15 MB before submitting.

Auditoría de seguridad

Riesgo medio

v1 • 1/11/2026 Abrir el informe versionado

All 48 static findings are false positives involving Markdown, legitimate service links, placeholder syntax, credential storage documentation, or model routing. A separate concern is unsafe prompt substitution into shell examples despite a blanket claim that prompt content cannot cause shell injection. No evidence found of malicious intent; CLI privacy and security claims cannot be verified from this documentation-only package.

Archivos escaneados

186

Líneas analizadas

Elementos de revisión

Falsos positivos ignorados

Preocupaciones de seguridad confirmadas (1)

Medio

SKILL.md:66-69 SKILL.md:87-94 SKILL.md:182

Unsafe Prompt Substitution in Shell Examples

Examples place prompt placeholders inside single-quoted shell arguments, while line 182 states: "No shell injection surface from prompt content." Direct substitution of untrusted prompt text containing a single quote can escape the argument and execute shell syntax before the CLI receives JSON.

The shell templates and blanket assurance are directly visible. Exploitation depends on unsafe substitution by the calling agent; no CLI implementation is included.

Factores de riesgo

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/prime-skills-wan-2-7/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Insignia Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/prime-skills-wan-2-7/security.svg)](https://skillstore.io/skills/prime-skills-wan-2-7?utm_source=security_passport_badge)

Insignia HTML

<a href="https://skillstore.io/skills/prime-skills-wan-2-7?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/prime-skills-wan-2-7/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Tarjeta para insertar

<iframe src="https://skillstore.io/embed/skills/prime-skills-wan-2-7.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

prime-skills. (2026). wan-2-7 security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/prime-skills-wan-2-7/audits/1

Cita BibTeX

@techreport{prime-skills-prime-skills-wan-2-7-2026,
  author = {prime-skills},
  title = {wan-2-7 security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/prime-skills-wan-2-7/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: "wan-2-7 security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "prime-skills"
date-released: "2026-11-01"
url: "https://skillstore.io/skills/prime-skills-wan-2-7/audits/1"
identifiers:
  - type: other
    value: "skillstore:prime-skills-wan-2-7:audit:1"
    description: "Skillstore immutable audit report identifier"

Comparar variantes

4 variantes instalables

Cada autor sigue siendo un skill instalable independiente. La variante recomendada se ordena según la evidencia de Skillstore.

Por qué esta variante es la primera

Mayor puntuación de Skillstore

Autor / fuente Puntuación de Skillstore Confianza de la evidencia Uso en Skillstore Actualizado

runcomfy-com Recomendado

runcomfy-com-wan-2-7

Puntuación de Skillstore 78

Confianza de la evidencia Alto

Uso en Skillstore 48

Actualizado

2026-09-09

prime-skills Actual

prime-skills-wan-2-7

Puntuación de Skillstore 69

Confianza de la evidencia Medio

Uso en Skillstore Desconocido

Actualizado

2026-11-01

doany-ai

doany-ai-wan-2-7

Puntuación de Skillstore 50

Confianza de la evidencia Alto

Uso en Skillstore 45

Actualizado

2026-09-09

agentspace-so

agentspace-so-wan-2-7

Puntuación de Skillstore 50

Confianza de la evidencia Alto

Uso en Skillstore 13

Actualizado

2026-10-22

Puntuación de Skillstore

Por qué esta puntuación Confianza de la evidencia: Medio

Arquitectura

Mantenibilidad

Contenido

Comunidad

Cumplimiento de la especificación

Lo que puedes crear

Product Motion Concepts

Prepare short product showcase requests with deliberate camera motion and targeted negative prompts.

Localized Spokesperson Clips

Reuse a visual prompt with different approved voiceover URLs to request language-specific lip-synced clips.

Vertical Social Video

Configure 9:16 clips with one primary action and controlled duration for social content experiments.

Prueba estos prompts

First Product Clip

Use Wan 2.7 to prepare a five-second product video of [product], with soft studio lighting and a slow camera push-in.

Vertical Motion Study

Prepare an eight-second 9:16 Wan 2.7 clip showing [subject] performing [single action]. Use 720p and exclude subtitles and flicker.

Audio-Driven Spokesperson

Prepare a 12-second Wan 2.7 spokesperson request using [approved audio URL]. Check audio constraints and use 9:16 framing with a locked camera.

Controlled Prompt Variants

Prepare three Wan 2.7 prompt variants for [scene]. Disable expansion, reuse seed [seed], and serialize inputs safely without shell interpolation.

Mejores prácticas

Specify camera motion and one primary action before adding lighting or style details.
Use approved media, check audio constraints, and avoid sending confidential content to the remote service.
Serialize JSON and pass CLI arguments without shell interpolation; disable expansion when exact prompt wording matters.

Evitar

Substituting untrusted prompt text directly into single-quoted shell examples.
Requesting native 4K, clips longer than 15 seconds, or unsupported audio formats.
Assuming multi-reference inputs work without checking the current provider schema.

Preguntas frecuentes

What must I install before using this skill?

Install the RunComfy CLI and authenticate with a RunComfy account. The skill itself supplies documentation, not the model or CLI.

Which durations and resolutions are documented?

The documented duration range is 2 to 15 whole seconds. Resolution options are 720p and 1080p.

Can I supply my own voiceover?

Yes. Supply an audio URL for a WAV or MP3 file lasting 3 to 30 seconds and no larger than 15 MB.

Can I prevent automatic prompt rewriting?

Yes. Disable prompt expansion when preparing the request to preserve literal prompt wording.

Does the documented schema support multiple reference files?

The text claims multi-reference support, but its schema lists no reference-media parameters. Check the current provider documentation before relying on that capability.

Does generation run locally?

No. The local CLI submits model inputs to RunComfy and downloads generated results. Review provider privacy terms before sending sensitive material.

Detalles del desarrollador

Autor

prime-skills

Licencia

MIT

Revisión de Skillstore

Aviso de versión

El autor no declaró una versión.

Repositorio

https://github.com/prime-skills/runcomfy-agent-skills/tree/fca19ae084c2ae4667f5c8affbb99da5103d5832/wan-2-7

Ref.

7a28cf6b8dd48b7ab254b03ef18bf31a583220ec

Actualidad del mantenimiento

1/11/2026

Uso

0 descargas · 0 vistas

Estructura de archivos

📄 SKILL.md