스킬 happyhorse-1-0

📦

happyhorse-1-0

Name: happyhorse-1-0
Author: runcomfy-com

콘텐츠 리비전 r1 높은 위험 ⚙️ 외부 명령어🌐 네트워크 접근📁 파일 시스템 접근

Generar videos de HappyHorse en RunComfy

La configuración de texto a video puede ser poco clara cuando los parámetros del modelo, las duraciones y los ajustes de salida difieren. Esta skill guía los prompts de HappyHorse 1.0 y las llamadas de la CLI de RunComfy.

지원: Claude Codex Code(CC)

⚠️ 38 나쁨

Maintain this Skill? Claim it ⚠️ 38 나쁨

설치 전에 중지하고 확인을 요청하세요.

계획을 검토하고 파일을 변경하기 전에 사용자의 명시적 동의를 받으세요.

내 에이전트로 설치

이 요청을 에이전트에 복사하세요. 공식 Skill 페이지와 매니페스트가 포함되어 있습니다.

에이전트 요청

Review the Skillstore skill "happyhorse-1-0" from https://skillstore.io/skills/runcomfy-com-happyhorse-1-0.md and its manifest at https://skillstore.io/api/skills/runcomfy-com-happyhorse-1-0/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

에이전트는 계속해서 계획을 표시하고 보안 정책에서 요구하는 확인을 요청해야 합니다.

에이전트가 읽기 쉬운 리소스

AI 에이전트, 크롤러, 스크립트가 전체 페이지 대신 정리된 컨텍스트만 필요할 때 이 링크를 사용하세요.

Markdown 상세 GET /skills/runcomfy-com-happyhorse-1-0.md 서명된 manifest GET /api/skills/runcomfy-com-happyhorse-1-0/manifest 서명된 lockfile GET /api/skills/runcomfy-com-happyhorse-1-0/lockfile

테스트해 보기

"happyhorse-1-0" 사용 중입니다. Genera un clip de cinco segundos en 16:9 de un corredor cruzando un puente bajo la lluvia.

예상 결과:

La skill prepara una solicitud de HappyHorse 1.0 usando la resolución 1080p predeterminada, una duración de cinco segundos y un prompt centrado en el movimiento.

"happyhorse-1-0" 사용 중입니다. Crea un anuncio vertical de cafetería sin marca de agua y con audio cálido.

예상 결과:

La skill selecciona el formato 9:16, desactiva la marca de agua, añade ambiente de cafetería y mantiene la escena centrada en una acción clara.

"happyhorse-1-0" 사용 중입니다. Explica por qué mi solicitud falló con una duración de 30 segundos.

예상 결과:

La skill identifica una incompatibilidad de esquema porque HappyHorse admite clips de 3 a 15 segundos y sugiere dividir la escena.

보안 감사

높은 위험

v4 • 2026. 7. 5. 버전별 보고서 열기

Most static findings are false positives from Markdown backticks, fenced examples, and abbreviated HTTP paths. Confirmed residual risk is limited to intended RunComfy CLI execution and network submission of prompts and bearer-token-authenticated requests. A high-confidence semantic supply-chain issue remains because install instructions reference a different GitHub repository than the reviewed source metadata.

스캔된 파일

196

분석된 줄 수

검토 항목

오탐 무시됨

확인된 보안 우려 사항 (1)

높음

SKILL.md:20 SKILL.md:25

Repository Mismatch in Installation Instructions

The skill links to and installs from agentspace-so/runcomfy-skills while the reviewed source metadata points to runcomfy-com/skills. This can route users to code that differs from the reviewed source.

The GitHub link and npx install command name agentspace-so/runcomfy-skills, while the report metadata identifies runcomfy-com/skills as the reviewed source. This is a clear supply-chain consistency issue, although ownership relationship is not proven from the file alone.

기능 검토 항목 (9)

이 스킬에 대해 예상될 수 있는 실제 로컬 기능이므로 검토가 필요하지만, 확인된 악의적 동작으로는 집계되지 않습니다.

중간

SKILL.md:10

Ruby/shell backtick execution

Calls `runcomfy run happyhorse/happyhorse-1-0/text-to-video` through

The skill states that it calls the local RunComfy CLI to launch a hosted text-to-video job. The command is fixed and legitimate, but it is still an external process that sends user content outside the local environment.

중간

SKILL.md:24-26

Ruby/shell backtick execution

```bash

The fenced block contains an npx/global skill installation command. This appears legitimate, but running it executes external tooling and should require explicit user confirmation.

중간

SKILL.md:44-45

Ruby/shell backtick execution

1. **RunComfy CLI** — `npm i -g @runcomfy/cli`

Line 44 instructs users to install the RunComfy CLI globally through npm. This is a normal prerequisite, but it executes package manager code outside the skill itself.

중간

SKILL.md:45-46

Ruby/shell backtick execution

2. **RunComfy account** — `runcomfy login` opens a browser device-code flow.

Line 45 instructs users to run runcomfy login, which starts an authentication flow for account access. The action is expected, but it handles credentials and should be user-approved.

중간

SKILL.md:65-69

Ruby/shell backtick execution

```bash

The command example invokes runcomfy with user-supplied prompt data and an output directory. The CLI target is fixed, but this is real external command execution.

중간

SKILL.md:73-82

Ruby/shell backtick execution

```bash

The vertical-video example invokes runcomfy with prompt data and generation settings. It is legitimate product behavior, but it still launches a local external command.

중간

SKILL.md:86-90

Ruby/shell backtick execution

```bash

The cheaper test-pass example invokes runcomfy with prompt data and generation settings. The command is fixed, but an agent could execute it locally if authorized.

중간

SKILL.md:178-179

Ruby/shell backtick execution

1. The skill invokes `runcomfy run happyhorse/happyhorse-1-0/text-to-video` with a JSON body matchin

The skill explicitly says it invokes runcomfy run with a JSON body. This is intended external CLI behavior rather than arbitrary execution, so the risk is limited but real.

낮음

SKILL.md:179

Hardcoded URL

2. The CLI POSTs to `https://model-api.runcomfy.net/v1/models/happyhorse/happyhorse-1-0/text-to-vide

Line 179 identifies a POST to the RunComfy model API using the user bearer token. This is intended service use, but it is real network egress of prompt data and credentials.

위험 요인

⚙️ 외부 명령어 (40)

🌐 네트워크 접근 (4)

SKILL.md:14 SKILL.md:20 SKILL.md:174 SKILL.md:179

📁 파일 시스템 접근 (5)

SKILL.md:180 SKILL.md:181 SKILL.md:182 SKILL.md:191 SKILL.md:191

감사자: codex 감사 이력 보기 →

이 보고서 공유 및 인용

버전이 지정된 평가 보고서, 중립 배지, 임베드 카드 및 인용을 공유하세요. Skillstore는 근거를 보고하지만 이 Skill의 안전 여부를 판단하지 않습니다.

버전별 보고서 열기

보고서 링크 복사

https://skillstore.io/skills/runcomfy-com-happyhorse-1-0/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 배지

[![Skillstore security assessment](https://skillstore.io/badges/skills/runcomfy-com-happyhorse-1-0/security.svg)](https://skillstore.io/skills/runcomfy-com-happyhorse-1-0?utm_source=security_passport_badge)

HTML 배지

<a href="https://skillstore.io/skills/runcomfy-com-happyhorse-1-0?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/runcomfy-com-happyhorse-1-0/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

임베드 카드

<iframe src="https://skillstore.io/embed/skills/runcomfy-com-happyhorse-1-0.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

학술 인용 (APA · BibTeX · CFF)

APA 인용

runcomfy-com. (2026). happyhorse-1-0 security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/runcomfy-com-happyhorse-1-0/audits/4

BibTeX 인용

@techreport{runcomfy-com-runcomfy-com-happyhorse-1-0-2026,
  author = {runcomfy-com},
  title = {happyhorse-1-0 security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/runcomfy-com-happyhorse-1-0/audits/4},
  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: "happyhorse-1-0 security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "runcomfy-com"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/runcomfy-com-happyhorse-1-0/audits/4"
identifiers:
  - type: other
    value: "skillstore:runcomfy-com-happyhorse-1-0:audit:4"
    description: "Skillstore immutable audit report identifier"

변형 비교

설치 가능한 변형 4개

각 작성자의 스킬은 별도의 설치 항목으로 유지됩니다. 추천 변형은 Skillstore 근거로 순위가 정해집니다.

이 변형이 1위인 이유

Skillstore 점수가 가장 높음

작성자 / 소스 Skillstore 점수 증거 신뢰도 Skillstore 사용량 업데이트됨

prime-skills 권장

prime-skills-happyhorse-1-0

Skillstore 점수 69

증거 신뢰도 중간

Skillstore 사용량 3

업데이트됨

2026-10-24

doany-ai

doany-ai-happyhorse-1-0

Skillstore 점수 50

증거 신뢰도 높음

Skillstore 사용량 53

업데이트됨

2026-09-09

agentspace-so

agentspace-so-happyhorse-1-0

Skillstore 점수 50

증거 신뢰도 높음

Skillstore 사용량 12

업데이트됨

2026-10-22

runcomfy-com 현재

runcomfy-com-happyhorse-1-0

Skillstore 점수 38

증거 신뢰도 중간

Skillstore 사용량 45

업데이트됨

2026-09-09

Skillstore 점수

이 점수의 이유 증거 신뢰도: 중간

아키텍처

유지보수성

콘텐츠

커뮤니티

사양 준수

만들 수 있는 것

Prototipar anuncios de video cortos

Crea conceptos de anuncios verticales o panorámicos con movimiento, dirección de cámara y ambiente sincronizado.

Crear clips conceptuales cinematográficos

Boceta escenas cinematográficas cortas con personajes consistentes, referencias de vestuario y dirección de sonido específica de la escena.

Probar prompts de video en automatización

Ejecuta pruebas repetibles de prompts de HappyHorse con parámetros fijos, seeds y carpetas de salida.

이 프롬프트를 사용해 보세요

Clip de video básico

Usa HappyHorse 1.0 para generar un video 1080p de 5 segundos en 16:9. Escena: [describe the motion, setting, and audio]. Guarda las salidas en [folder].

Video social vertical corto

Genera un video de HappyHorse de 8 segundos en 9:16 sin marca de agua. Incluye movimiento de cámara, una acción clara y audio ambiental. Escena: [details].

Prueba de personaje en múltiples tomas

Crea un video de HappyHorse de 10 segundos con dos tomas. Mantén [character, wardrobe, and prop] consistente en ambas tomas y luego describe cómo cambia la acción.

Ejecución comparativa de producción

Crea tres variantes de HappyHorse en 720P usando seeds [seed list]. Mantén el mismo prompt, compara las salidas y recomienda la mejor versión para la generación final en 1080p.

모범 사례

Describe el movimiento a lo largo del tiempo con indicaciones claras de cámara y audio.
Mantén los prompts por debajo de 2.500 caracteres y usa solo ajustes de salida compatibles.
Usa 720P, duración corta y seeds fijas para las primeras pruebas de prompts.

피하기

Usar descripciones de imágenes estáticas que no explican el movimiento.
Combinar muchas acciones no relacionadas o estilos visuales contradictorios en un solo clip.
Enviar requisitos de audio externo o de imagen a video a este endpoint solo de texto.

자주 묻는 질문

¿Esta skill requiere una cuenta de RunComfy?

Sí. Necesitas la CLI de RunComfy, una cuenta de RunComfy y autenticación válida antes de que pueda ejecutarse la generación.

¿Qué endpoint de HappyHorse cubre?

Cubre el endpoint de texto a video de HappyHorse 1.0 en RunComfy.

¿Puede crear audio con el video?

Sí. Admite dirección de audio dentro del pase mediante el prompt, pero no acepta entrada de audio externa.

¿Qué duraciones de clip son compatibles?

El rango de duración documentado es de 3 a 15 segundos.

¿Dónde se guardan los videos generados?

La CLI de RunComfy descarga las salidas generadas en el directorio de salida seleccionado para la ejecución.

¿Qué revisión de seguridad se necesita antes de usarla?

Confirma la fuente de instalación, aprueba la ejecución de la CLI de RunComfy y espera que los prompts y la autenticación se envíen a RunComfy.

개발자 세부 정보

작성자

runcomfy-com

라이선스

MIT

Skillstore 리비전

버전 안내

작성자가 버전을 선언하지 않았습니다.

리포지토리

https://github.com/runcomfy-com/skills/tree/main/happyhorse-1-0/

참조

62e2a730c5cd74eab4c7164309d810de660fcea3

유지보수 최신성

2026. 7. 18.

사용량

2 다운로드 · 0 조회

파일 구조

📄 SKILL.md