스킬 gpt-image-edit
📦
gpt-image-edit
콘텐츠 리비전 r1 높은 위험 ⚙️ 외부 명령어🌐 네트워크 접근📁 파일 시스템 접근
Editar imágenes con GPT Image 2 en RunComfy
Las ediciones de imagen dirigidas suelen desviarse, especialmente con rostros, marcas y texto. Esta skill proporciona patrones de RunComfy CLI para ediciones con GPT Image 2 mediante prompts centrados en la preservación.
지원: Claude Codex Code(CC)
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 "gpt-image-edit" from https://skillstore.io/skills/doany-ai-gpt-image-edit.md and its manifest at https://skillstore.io/api/skills/doany-ai-gpt-image-edit/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.
테스트해 보기
"gpt-image-edit" 사용 중입니다. Un retrato necesita un fondo de estudio neutro sin cambiar a la persona.
예상 결과:
Un prompt de edición listo para comando que prioriza el rostro, la pose, la ropa y el reemplazo del fondo.
"gpt-image-edit" 사용 중입니다. El titular de un póster debe reescribirse en japonés preservando el diseño original.
예상 결과:
Un prompt que cita el texto japonés y limita la edición al área del titular.
"gpt-image-edit" 사용 중입니다. Un producto debe colocarse en una habitación de una segunda imagen de referencia.
예상 결과:
Un prompt con múltiples referencias que identifica image 1 como el sujeto e image 2 como la escena.
보안 감사
높은 위험v4 • 2026. 7. 5. 버전별 보고서 열기
Most static backtick and path traversal alerts are Markdown formatting or placeholder URLs rather than executable code. Confirmed risks are the intended use of the RunComfy CLI, third-party network processing, and a source mismatch that points users to another repository. No prompt injection attempt was found in SKILL.md.
1
스캔된 파일
184
분석된 줄 수
13
검토 항목
0
오탐 무시됨
확인된 보안 우려 사항 (2)
높음
Install Source Mismatch
SKILL.md links and install instructions point to agentspace-so/runcomfy-skills while this audit targets doany-ai/gpt-image-edit. Users could install a different repository than the reviewed package.
The GitHub link and install command both name agentspace-so/runcomfy-skills. The audited source metadata names doany-ai, so the mismatch is direct and reproducible.
중간
Third-Party Image Processing Boundary
The skill sends prompts to model-api.runcomfy.net and says image URLs are fetched by the RunComfy model server. This exposes prompts, image URLs, and generated outputs to a third-party service.
The file explicitly describes the outbound model API call and remote fetching of image URLs. This is expected functionality, but it is a clear privacy boundary.
기능 검토 항목 (13)
이 스킬에 대해 예상될 수 있는 실제 로컬 기능이므로 검토가 필요하지만, 확인된 악의적 동작으로는 집계되지 않습니다.
중간
Ruby/shell backtick execution
`runcomfy run openai/gpt-image-2/edit` through the local RunComfy CLI.
Line 13 states the skill calls the local RunComfy CLI. That is intended functionality, but it executes a third-party command from the user environment.
중간
Ruby/shell backtick execution
```bash
The code block contains an npx skills install command from a GitHub repository. If followed, it triggers package and repository installation outside the skill content itself.
중간
Ruby/shell backtick execution
1. **RunComfy CLI** — `npm i -g @runcomfy/cli`
Line 45 instructs users to globally install the RunComfy CLI with npm. Global package installation is a real supply-chain and local execution risk.
중간
Ruby/shell backtick execution
2. **RunComfy account** — `runcomfy login` opens a browser device-code flow.
Line 46 instructs users to run RunComfy login, which starts an authentication flow. This is expected, but it is still external command execution involving credentials.
중간
Ruby/shell backtick execution
```bash
The command block runs runcomfy with user image input and an output directory. It is legitimate for this skill, but it is a concrete external command invocation.
중간
Ruby/shell backtick execution
```bash
The command block runs runcomfy for a multilingual edit and sends image input to the service. It is a real external command, even though the example is documented.
중간
Ruby/shell backtick execution
```bash
The command block runs runcomfy for a multi-reference edit with external image URLs. This is intended, but it is still external command execution.
중간
Ruby/shell backtick execution
The skill invokes `runcomfy run openai/gpt-image-2/edit` with a JSON body matching the schema. The C
Line 175 explicitly states that the skill invokes runcomfy run and downloads generated outputs. This confirms the external command behavior described by the skill.
중간
Ruby/shell backtick execution
- **Token storage**: `runcomfy login` writes the API token to `~/.config/runcomfy/token.json` with m
Line 179 refers to running RunComfy login and writing an API token. The command is expected, but it handles credentials on the local machine.
낮음
Hardcoded URL
"images": ["https://.../portrait.jpg"]
The example image URL is a placeholder, not a fixed malicious endpoint. It still demonstrates that user image URLs are supplied to a remote model service.
낮음
Hardcoded URL
"images": ["https://.../poster-en.jpg"]
The example poster URL is a placeholder, but it documents remote image input for the model request. This is an expected low-severity network privacy consideration.
낮음
Hardcoded URL
"images": ["https://.../subject.jpg", "https://.../room.jpg"]
The multi-reference example uses placeholder HTTPS image URLs. The endpoint is not hardcoded here, but the example confirms remote image references are part of use.
낮음
Hardcoded URL
The skill invokes `runcomfy run openai/gpt-image-2/edit` with a JSON body matching the schema. The C
Line 175 names the RunComfy model API endpoint and output download domains. This is a real outbound network dependency for prompts, image URLs, and generated outputs.
위험 요인
⚙️ 외부 명령어 (38)
SKILL.md:5 SKILL.md:13 SKILL.md:24 SKILL.md:26-28 SKILL.md:28-40 SKILL.md:40-45 SKILL.md:45-46 SKILL.md:46-47 SKILL.md:47 SKILL.md:51-55 SKILL.md:55-56 SKILL.md:56-57 SKILL.md:57 SKILL.md:59-65 SKILL.md:65-72 SKILL.md:72-76 SKILL.md:76-83 SKILL.md:83-87 SKILL.md:87-94 SKILL.md:94-98 SKILL.md:98-100 SKILL.md:100 SKILL.md:102 SKILL.md:104 SKILL.md:106-112 SKILL.md:112 SKILL.md:128-133 SKILL.md:133-137 SKILL.md:137-142 SKILL.md:142-146 SKILL.md:146-150 SKILL.md:150-154 SKILL.md:154 SKILL.md:155-175 SKILL.md:175 SKILL.md:179 SKILL.md:180-182 SKILL.md:182
🌐 네트워크 접근 (7)
📁 파일 시스템 접근 (6)
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.
보고서 링크 복사
https://skillstore.io/skills/doany-ai-gpt-image-edit/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 배지
[](https://skillstore.io/skills/doany-ai-gpt-image-edit?utm_source=security_passport_badge)HTML 배지
<a href="https://skillstore.io/skills/doany-ai-gpt-image-edit?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/doany-ai-gpt-image-edit/security.svg" alt="Skillstore security assessment" loading="lazy"></a>임베드 카드
<iframe src="https://skillstore.io/embed/skills/doany-ai-gpt-image-edit.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
doany-ai. (2026). gpt-image-edit security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/doany-ai-gpt-image-edit/audits/4BibTeX 인용
@techreport{doany-ai-doany-ai-gpt-image-edit-2026,
author = {doany-ai},
title = {gpt-image-edit security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/doany-ai-gpt-image-edit/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: "gpt-image-edit security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "doany-ai"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/doany-ai-gpt-image-edit/audits/4"
identifiers:
- type: other
value: "skillstore:doany-ai-gpt-image-edit:audit:4"
description: "Skillstore immutable audit report identifier"
변형 비교
설치 가능한 변형 4개각 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-gpt-image-edit
Skillstore 점수 77
증거 신뢰도 중간
Skillstore 사용량 4
업데이트됨
2026-10-24
runcomfy-com-gpt-image-edit
Skillstore 점수 70
증거 신뢰도 높음
Skillstore 사용량 46
업데이트됨
2026-09-09
agentspace-so-gpt-image-edit
Skillstore 점수 50
증거 신뢰도 높음
Skillstore 사용량 15
업데이트됨
2026-10-22
Skillstore 점수
이 점수의 이유 증거 신뢰도: 중간 55
아키텍처
85
유지보수성
85
콘텐츠
67
커뮤니티
83
사양 준수
만들 수 있는 것
Localizar creatividad publicitaria
Reemplazar titulares de imagen en otro idioma mientras se preservan el diseño, la colocación del producto y los elementos de marca.
Preparar variantes de producto
Cambiar fondos o texto de una imagen de producto manteniendo estable el producto principal.
Componer imágenes de referencia
Combinar un sujeto de una imagen con una escena o paleta de otras referencias.
이 프롬프트를 사용해 보세요
Cambio de fondo para principiantes
Keep the main subject, pose, clothing, and brand marks unchanged. Replace only the background with a clean studio setting.
Edición de titular localizado
Keep the photo, layout, lighting, and logo unchanged. Replace only the headline with "Your translated text" in the same position.
Composición con múltiples referencias
Use the subject from image 1 and the room style from image 2. Match lighting and preserve subject identity.
Revisión precisa del diseño
Keep the product and brand assets unchanged. Move the headline to the bottom center, update the CTA text, and preserve spacing.
모범 사례
- Indica los requisitos de preservación antes del cambio solicitado.
- Cita el texto exacto dentro de la imagen y nombra la escritura o el idioma.
- Usa size auto a menos que la edición requiera una nueva relación de aspecto.
피하기
- Combinar muchas ediciones no relacionadas en un solo prompt largo.
- Usar instrucciones vagas como hacerlo mejor o mejorar la imagen.
- Pasar imágenes privadas mediante URLs públicas sin aprobación.
자주 묻는 질문
¿Esta skill genera imágenes desde cero?
No. Se centra en editar imágenes existentes mediante el endpoint GPT Image 2 edit.
¿Qué herramientas admite?
Está marcada como compatible con Claude, Codex y Claude Code.
¿Necesito una cuenta de RunComfy?
Sí. El flujo de trabajo requiere RunComfy CLI y autenticación antes de que funcionen las llamadas al modelo.
¿Puede editar texto dentro de una imagen?
Sí. Las instrucciones enfatizan citar el texto exacto de reemplazo y preservar el diseño circundante.
¿Cuántas imágenes de referencia puedo usar?
La skill documenta hasta diez URLs públicas HTTPS de imágenes para una solicitud de edición.
¿Dónde se procesan las imágenes?
Los prompts y las URLs de imágenes se envían a endpoints de la API de modelos de RunComfy para su procesamiento.