Habilidades ai-video-generation

📦

ai-video-generation

Name: ai-video-generation
Author: genmedia-labs

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

Generate AI Videos with RunComfy

Choosing and prompting video models requires detailed model knowledge. This skill routes each request and prepares focused RunComfy CLI invocations.

Compatible con: Claude Codex Code(CC)

⚠️ 50 Deficiente

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 "ai-video-generation" from https://skillstore.io/skills/genmedia-labs-ai-video-generation.md and its manifest at https://skillstore.io/api/skills/genmedia-labs-ai-video-generation/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/genmedia-labs-ai-video-generation.md Manifest firmado GET /api/skills/genmedia-labs-ai-video-generation/manifest Lockfile firmado GET /api/skills/genmedia-labs-ai-video-generation/lockfile

Pruébalo

Usando "ai-video-generation". Create an eight-second widescreen clip of a red kite crossing a windy beach with natural ambient audio.

Resultado esperado:

Selected model: HappyHorse 1.0 for general text-to-video with synchronized audio.
Prompt: A red kite tumbles across a windy beach at golden hour while children chase it. Audio includes wind, gulls, surf, and distant laughter.
Output destination: ./out

Usando "ai-video-generation". Animate my portrait into a six-second vertical clip with a slow head turn and stable camera.

Resultado esperado:

Selected route: image-to-video.
Motion direction: The subject slowly turns toward the camera and smiles while the camera remains still.
Format: six seconds, vertical 9:16.

Usando "ai-video-generation". Create a realistic product rotation and keep the background motionless.

Resultado esperado:

Selected model: Veo 3-1 for controlled physical motion and object permanence.
Direction: The product rotates 180 degrees on its surface. The camera and all background elements remain still.

Auditoría de seguridad

Riesgo medio

v1 • 13/8/2026 Abrir el informe versionado

The skill intentionally installs and invokes the RunComfy CLI, sends prompts and referenced media to a third-party API, and downloads generated files. Most static alerts are false positives caused by Markdown backticks, visible documentation links, and model-selection prose; token storage is documented with restrictive permissions.

Archivos escaneados

425

Líneas analizadas

Elementos de revisión

Falsos positivos ignorados

Preocupaciones de seguridad confirmadas (1)

Medio

SKILL.md:199-213 SKILL.md:402-412

Third-Party Processing of Prompts and Media

The workflow sends prompts and user-selected media URLs to RunComfy model endpoints, where external services process the content. Users must avoid confidential or unauthorized media.

The documented audio_url example and the How it works section explicitly describe API submission, polling, and remote result retrieval.

Elementos de revisión de capacidades (17)

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

Alto

SKILL.md:407

Hidden file in home directory

- **Token storage**: `runcomfy login` writes the API token to `~/.config/runcomfy/token.json` with m

The skill documents that runcomfy login stores an API token at ~/.config/runcomfy/token.json. This is intentional credential-file access, mitigated by the stated mode 0600 and environment-variable alternative.

Medio

SKILL.md:32-43

Ruby/shell backtick execution

```bash

This fenced setup example instructs users to install the RunComfy CLI, authenticate, and invoke a remote model. These are intentional external commands, although their purpose is consistent with the skill.

Medio

SKILL.md:49-51

Ruby/shell backtick execution

```bash

This fenced example instructs users to run npx to install the community skill globally. It is a real external package-manager command with network and supply-chain exposure.

Medio

SKILL.md:174-183

Ruby/shell backtick execution

```bash

This fenced example invokes runcomfy to submit generation input to a selected remote model and write results under ./out. The external command is the skill's declared core behavior.

Medio

SKILL.md:205-213

Ruby/shell backtick execution

```bash

This fenced example invokes runcomfy to submit generation input to a selected remote model and write results under ./out. The external command is the skill's declared core behavior.

Medio

SKILL.md:217-221

Ruby/shell backtick execution

```bash

This fenced example invokes runcomfy to submit generation input to a selected remote model and write results under ./out. The external command is the skill's declared core behavior.

Medio

SKILL.md:239-247

Ruby/shell backtick execution

```bash

This fenced example invokes runcomfy to submit generation input to a selected remote model and write results under ./out. The external command is the skill's declared core behavior.

Medio

SKILL.md:264-273

Ruby/shell backtick execution

```bash

This fenced example invokes runcomfy to submit generation input to a selected remote model and write results under ./out. The external command is the skill's declared core behavior.

Medio

SKILL.md:292-299

Ruby/shell backtick execution

```bash

This fenced example invokes runcomfy to submit generation input to a selected remote model and write results under ./out. The external command is the skill's declared core behavior.

Medio

SKILL.md:324-331

Ruby/shell backtick execution

```bash

This fenced example invokes runcomfy to submit generation input to a selected remote model and write results under ./out. The external command is the skill's declared core behavior.

Medio

SKILL.md:402

Ruby/shell backtick execution

The skill classifies the user request into one of the t2v / i2v / extend routes above and invokes `r

The source explicitly states that the skill invokes runcomfy, which posts to the RunComfy API and downloads generated files. This confirms intended external-command and remote-service behavior.

Medio

SKILL.md:406

Ruby/shell backtick execution

- **Install via verified package manager only.** Use `npm i -g @runcomfy/cli` or `npx -y @runcomfy/c

The text explicitly recommends npm or npx commands to install the RunComfy CLI. Package installation is intentional external command execution with normal supply-chain risk.

Medio

SKILL.md:407

Hidden file access

- **Token storage**: `runcomfy login` writes the API token to `~/.config/runcomfy/token.json` with m

Bajo

SKILL.md:209

Hardcoded URL

"audio_url": "https://your-cdn.example/voiceover.mp3",

This example supplies a user-hosted media URL to a RunComfy model request, causing the remote service to fetch that asset. The network use is expected but may disclose the media and its location.

Bajo

SKILL.md:267

Hardcoded URL

"image_url": "https://your-cdn.example/portrait.jpg",

This example supplies a user-hosted media URL to a RunComfy model request, causing the remote service to fetch that asset. The network use is expected but may disclose the media and its location.

Bajo

SKILL.md:295

Hardcoded URL

"image_url": "https://your-cdn.example/product.jpg",

This example supplies a user-hosted media URL to a RunComfy model request, causing the remote service to fetch that asset. The network use is expected but may disclose the media and its location.

Bajo

SKILL.md:327

Hardcoded URL

"image_url": "https://your-cdn.example/character.jpg",

This example supplies a user-hosted media URL to a RunComfy model request, causing the remote service to fetch that asset. The network use is expected but may disclose the media and its location.

Factores de riesgo

⚙️ Comandos externos (50)

SKILL.md:6 SKILL.md:16 SKILL.md:26 SKILL.md:32-43 SKILL.md:43-45 SKILL.md:45-49 SKILL.md:49-51 SKILL.md:51-59 SKILL.md:59-64 SKILL.md:64-69 SKILL.md:69-74 SKILL.md:74-79 SKILL.md:79-80 SKILL.md:80-84 SKILL.md:84-89 SKILL.md:89-96 SKILL.md:96-101 SKILL.md:101-102 SKILL.md:102-106 SKILL.md:106-111 SKILL.md:111-116 SKILL.md:116-121 SKILL.md:121-126 SKILL.md:126-131 SKILL.md:131-136 SKILL.md:136-143 SKILL.md:143-147 SKILL.md:147-151 SKILL.md:151-157 SKILL.md:157-166 SKILL.md:166-167 SKILL.md:167-168 SKILL.md:168 SKILL.md:169 SKILL.md:170-174 SKILL.md:174-183 SKILL.md:183-188 SKILL.md:188-196 SKILL.md:196-197 SKILL.md:197-199 SKILL.md:199-205 SKILL.md:205-213 SKILL.md:213-217 SKILL.md:217-221 SKILL.md:221-232 SKILL.md:232 SKILL.md:233-239 SKILL.md:239-247 SKILL.md:247-252 SKILL.md:252-259

🌐 Acceso a red (47)

📁 Acceso al sistema de archivos (2)

SKILL.md:407 SKILL.md:407

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/genmedia-labs-ai-video-generation/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Insignia Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/genmedia-labs-ai-video-generation/security.svg)](https://skillstore.io/skills/genmedia-labs-ai-video-generation?utm_source=security_passport_badge)

Insignia HTML

<a href="https://skillstore.io/skills/genmedia-labs-ai-video-generation?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/genmedia-labs-ai-video-generation/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Tarjeta para insertar

<iframe src="https://skillstore.io/embed/skills/genmedia-labs-ai-video-generation.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

genmedia-labs. (2026). ai-video-generation security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/genmedia-labs-ai-video-generation/audits/1

Cita BibTeX

@techreport{genmedia-labs-genmedia-labs-ai-video-generation-2026,
  author = {genmedia-labs},
  title = {ai-video-generation security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/genmedia-labs-ai-video-generation/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: "ai-video-generation security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "genmedia-labs"
date-released: "2026-08-13"
url: "https://skillstore.io/skills/genmedia-labs-ai-video-generation/audits/1"
identifiers:
  - type: other
    value: "skillstore:genmedia-labs-ai-video-generation:audit:1"
    description: "Skillstore immutable audit report identifier"

Comparar variantes

23 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 uso en Skillstore

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

runcomfy-com Recomendado

runcomfy-com-ai-video-generation

Puntuación de Skillstore 78

Confianza de la evidencia Alto

Uso en Skillstore 24

Actualizado

2026-09-09

inferen-sh

inferen-sh-ai-video-generation

Puntuación de Skillstore 78

Confianza de la evidencia Alto

Uso en Skillstore 12

Actualizado

2026-09-09

inference-shell

inference-shell-ai-video-generation

Puntuación de Skillstore 78

Confianza de la evidencia Alto

Uso en Skillstore 12

Actualizado

2026-09-09

agentspace-so

agentspace-so-ai-video-generation

Puntuación de Skillstore 78

Confianza de la evidencia Alto

Uso en Skillstore 9

Actualizado

2026-09-09

doany-ai

doany-ai-ai-video-generation

Puntuación de Skillstore 78

Confianza de la evidencia Alto

Uso en Skillstore 8

Actualizado

2026-09-09

halt-catch-fire

halt-catch-fire-ai-video-generation

Puntuación de Skillstore 75

Confianza de la evidencia Alto

Uso en Skillstore 45

Actualizado

2026-09-09

inference-sh-skills

inference-sh-skills-ai-video-generation

Puntuación de Skillstore 75

Confianza de la evidencia Alto

Uso en Skillstore 8

Actualizado

2026-09-09

skills-collective

skills-collective-ai-video-generation

Puntuación de Skillstore 74

Confianza de la evidencia Medio

Uso en Skillstore 6

Actualizado

2026-09-09

tool-belt

tool-belt-ai-video-generation

Puntuación de Skillstore 69

Confianza de la evidencia Alto

Uso en Skillstore 10

Actualizado

2026-09-09

skills-shell

skills-shell-ai-video-generation

Puntuación de Skillstore 69

Confianza de la evidencia Alto

Uso en Skillstore 10

Actualizado

2026-09-09

inference-skills

inference-skills-ai-video-generation

Puntuación de Skillstore 69

Confianza de la evidencia Alto

Uso en Skillstore 6

Actualizado

2026-09-09

qu-skills

qu-skills-ai-video-generation

Puntuación de Skillstore 68

Confianza de la evidencia Alto

Uso en Skillstore 21

Actualizado

2026-09-09

tul-sh

tul-sh-ai-video-generation

Puntuación de Skillstore 50

Confianza de la evidencia Alto

Uso en Skillstore 19

Actualizado

2026-09-09

toolshell

toolshell-ai-video-generation

Puntuación de Skillstore 50

Confianza de la evidencia Alto

Uso en Skillstore 18

Actualizado

2026-09-09

skillssh

skillssh-ai-video-generation

Puntuación de Skillstore 50

Confianza de la evidencia Alto

Uso en Skillstore 13

Actualizado

2026-09-09

infsh-skills

infsh-skills-ai-video-generation

Puntuación de Skillstore 50

Confianza de la evidencia Alto

Uso en Skillstore 12

Actualizado

2026-09-09

danielgwilson

danielgwilson-ai-video-generation

Puntuación de Skillstore 50

Confianza de la evidencia Medio

Uso en Skillstore 6

Actualizado

2026-09-09

101-skills

101-skills-ai-video-generation

Puntuación de Skillstore 50

Confianza de la evidencia Medio

Uso en Skillstore 6

Actualizado

2026-09-09

genmedia-labs Actual

genmedia-labs-ai-video-generation

Puntuación de Skillstore 50

Confianza de la evidencia Medio

Uso en Skillstore 2

Actualizado

2026-09-09

inference-sh

inference-sh-ai-video-generation

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 37

Actualizado

2026-09-09

inference-sh-9

inference-sh-9-ai-video-generation

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 23

Actualizado

2026-09-09

inference-sh-8

inference-sh-8-ai-video-generation

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 9

Actualizado

2026-09-09

prime-skills

prime-skills-ai-video-generation

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 2

Actualizado

2026-09-09

Puntuación de Skillstore

Por qué esta puntuación Confianza de la evidencia: Medio

Arquitectura

Mantenibilidad

Contenido

Comunidad

Cumplimiento de la especificación

Lo que puedes crear

Produce Social Clips

Create short vertical clips from a prompt or still image with optional generated audio.

Animate Product Images

Turn product stills into controlled motion shots for reviews, advertisements, or concept tests.

Prototype Cinematic Sequences

Compare models and extend selected clips while preserving camera, motion, and character direction.

Prueba estos prompts

Create a Simple Clip

Generate a [duration]-second [aspect ratio] video of [subject] performing [action] in [setting]. Use [visual style].

Animate a Still Image

Animate this user-provided image: [image URL]. Add [subject motion] and [camera motion]. Keep [elements] fixed. Use [aspect ratio].

Create a Lip-Synced Scene

Create a [duration]-second scene using this user-provided voiceover: [audio URL]. Show [speaker description] in [setting] with [lighting].

Build a Multi-Reference Sequence

Use [image references] for identity, [video references] for motion, and [audio references] for sound. Create [shot sequence] with [lens and lighting direction]. Select the best model and explain the choice before running it.

Mejores prácticas

Confirm model choice, expected cost, and output settings before generation.
Use only media that the user owns or has permission to process.
Describe one main action, camera behavior, and audio requirements clearly.

Evitar

Do not expose API tokens in prompts, logs, repositories, or command history.
Do not upload confidential or unauthorized media to external model services.
Do not request many costly generations without confirming scope and budget.

Preguntas frecuentes

What does this skill generate?

It supports text-to-video, image-to-video, and selected video-extension workflows through RunComfy models.

Does it require a RunComfy account?

Yes. The RunComfy CLI requires authentication, network access, and sufficient service credits.

Can it generate synchronized audio?

Yes, for models that support generated audio or supplied audio for lip-sync.

Where are generated files saved?

The examples save downloaded results under the selected output directory, commonly ./out.

How should sensitive media be handled?

Do not submit confidential, regulated, or unauthorized media because external services process the inputs.

Can model results be guaranteed?

No. Quality, availability, pricing, duration, and schema support can vary by model and service version.

Detalles del desarrollador

Autor

genmedia-labs

Licencia

MIT

Revisión de Skillstore

Aviso de versión

El autor no declaró una versión.

Repositorio

https://github.com/genmedia-labs/skills/tree/9f1b4c229cb9e0c962f11ef24c8c87d5f004f393/ai-video-generation

Ref.

31b588eb921f5d9abe75b679d024f1258efde2de

Actualidad del mantenimiento

13/8/2026

Uso

0 descargas · 0 vistas

Estructura de archivos

📄 SKILL.md