📦
ai-music
77Create and Edit AI Music with RunComfy
Choosing a suitable music model and request format can require detailed platform knowledge. This skill routes each request and prepares the correct RunComfy workflow.
디자인 및 크리에이티브 보기
스킬 gpt-image-2
📦
gpt-image-2
콘텐츠 리비전 r1 높은 위험 ⚙️ 외부 명령어🌐 네트워크 접근📁 파일 시스템 접근
Create and Edit Images with GPT Image 2
Precise image generation and editing often requires model-specific inputs and prompt structure. This skill guides GPT Image 2 jobs through the RunComfy CLI.
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-2" from https://skillstore.io/skills/prime-skills-gpt-image-2.md and its manifest at https://skillstore.io/api/skills/prime-skills-gpt-image-2/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-2" 사용 중입니다. Create a square studio image of a ceramic bottle labeled "AQUA+" on a neutral background.
예상 결과:
A downloaded square product image with soft studio lighting, a centered bottle, and the requested short label.
"gpt-image-2" 사용 중입니다. Replace the room background with a bright studio while keeping the person's face, pose, and framing unchanged.
예상 결과:
An edited image that preserves the subject and composition while replacing the background.
"gpt-image-2" 사용 중입니다. Combine the subject from the first reference with the lighting and room from the second reference.
예상 결과:
A generated composite using the first image as the primary subject and the second image as environmental guidance.
보안 감사
높은 위험v1 • 2026. 8. 14. 버전별 보고서 열기
All 53 static findings are false positives caused by Markdown formatting, visible documentation URLs, prose ellipses, and documented CLI behavior. Semantic review found shell injection risk in prompt examples, unpinned global installers, and expected third-party prompt and image processing.
1
스캔된 파일
212
분석된 줄 수
0
검토 항목
0
오탐 무시됨
확인된 보안 우려 사항 (3)
높음
User Prompt Can Break Shell Quoting
The examples place a user prompt inside single-quoted shell JSON. An apostrophe can terminate the quote and permit shell command injection.
The command templates directly place the user-controlled prompt placeholder inside a shell single-quoted argument. No shell-safe encoding step is specified.
중간
Unpinned Global Installation Commands
The skill recommends unpinned package and skill installation with global scope. A compromised future release could execute with the user's privileges.
Both commands resolve mutable package or repository content without a version or commit. The global options increase the affected environment.
중간
Prompts and References Leave the Local System
Prompts and public image references are sent to RunComfy for processing. Sensitive prompts or reference URLs may expose private information.
The documentation explicitly states that prompts and reference URLs are submitted to the RunComfy Model API for remote processing.
위험 요인
⚙️ 외부 명령어 (41)
SKILL.md:9-10 SKILL.md:10 SKILL.md:24-26 SKILL.md:26-45 SKILL.md:45-46 SKILL.md:46-47 SKILL.md:47 SKILL.md:53-57 SKILL.md:57-58 SKILL.md:58 SKILL.md:60-64 SKILL.md:64-65 SKILL.md:65-66 SKILL.md:66 SKILL.md:68-74 SKILL.md:74-78 SKILL.md:78-82 SKILL.md:82-89 SKILL.md:89-93 SKILL.md:93-100 SKILL.md:100-102 SKILL.md:102 SKILL.md:106-109 SKILL.md:109-147 SKILL.md:147-151 SKILL.md:151-155 SKILL.md:155-159 SKILL.md:159-163 SKILL.md:163-168 SKILL.md:168-172 SKILL.md:172-179 SKILL.md:179-185 SKILL.md:185-194 SKILL.md:194-195 SKILL.md:195-196 SKILL.md:196 SKILL.md:197 SKILL.md:198 SKILL.md:207 SKILL.md:208-210 SKILL.md:210
🌐 네트워크 접근 (6)
📁 파일 시스템 접근 (5)
감사자: codex
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/prime-skills-gpt-image-2/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 배지
[](https://skillstore.io/skills/prime-skills-gpt-image-2?utm_source=security_passport_badge)HTML 배지
<a href="https://skillstore.io/skills/prime-skills-gpt-image-2?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/prime-skills-gpt-image-2/security.svg" alt="Skillstore security assessment" loading="lazy"></a>임베드 카드
<iframe src="https://skillstore.io/embed/skills/prime-skills-gpt-image-2.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
prime-skills. (2026). gpt-image-2 security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/prime-skills-gpt-image-2/audits/1BibTeX 인용
@techreport{prime-skills-prime-skills-gpt-image-2-2026,
author = {prime-skills},
title = {gpt-image-2 security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/prime-skills-gpt-image-2/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: "gpt-image-2 security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "prime-skills"
date-released: "2026-08-14"
url: "https://skillstore.io/skills/prime-skills-gpt-image-2/audits/1"
identifiers:
- type: other
value: "skillstore:prime-skills-gpt-image-2:audit:1"
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
runcomfy-com 권장
runcomfy-com-gpt-image-2
Skillstore 점수 78
증거 신뢰도 높음
Skillstore 사용량 27
업데이트됨
2026-09-09
agentspace-so-gpt-image-2
Skillstore 점수 38
증거 신뢰도 중간
Skillstore 사용량 64
업데이트됨
2026-10-22
prime-skills 현재
prime-skills-gpt-image-2
Skillstore 점수 38
증거 신뢰도 중간
Skillstore 사용량 7
업데이트됨
2026-09-09
Skillstore 점수
이 점수의 이유 증거 신뢰도: 중간 55
아키텍처
85
유지보수성
87
콘텐츠
65
커뮤니티
83
사양 준수
만들 수 있는 것
Build Product Visuals
Create product images with controlled lighting, readable labels, and consistent composition.
Localize Brand Assets
Replace short embedded text while preserving the source layout and brand elements.
Create Labeled Concepts
Generate interface mockups, posters, or technical illustrations with specific labels and layout cues.
이 프롬프트를 사용해 보세요
Simple Image
Create a [subject] in [setting]. Use [lighting], a [mood] mood, and a [square, portrait, or landscape] composition.
Product Image with Text
Create a product image of [item]. The label reads "[short text]" in [script or language]. Use [lighting] and [background].
Preserving Image Edit
Change [target element] to [desired result]. Keep [identity, pose, framing, typography, or brand mark] unchanged. Preserve the original aspect ratio.
Multi-Reference Composition
Use the subject from image 1 and [lighting, setting, or style] from image 2. Preserve [constraints]. Place [elements] at [positions].
모범 사례
- State the subject, setting, lighting, mood, and composition with concrete terms.
- Quote short embedded text exactly and name the required language or script.
- Change one attribute per edit and list every element that must remain unchanged.
피하기
- Do not combine conflicting instructions such as requesting both no text and a visible headline.
- Do not stack many unrelated styles in one prompt.
- Do not place untrusted prompt text directly inside a shell command.
자주 묻는 질문
Does this skill call OpenAI directly?
No. It uses the RunComfy CLI and RunComfy Model API to access GPT Image 2.
Which output sizes are supported?
Generation supports 1024 by 1024, 1024 by 1536, and 1536 by 1024. Editing also supports automatic aspect-ratio preservation.
Can it edit several reference images?
Yes. The edit endpoint accepts up to ten public HTTPS image URLs. The first image is the primary reference.
Can it render text inside an image?
Yes. Short quoted text works best. Name the language or script when generating multilingual text.
Where are generated images saved?
The RunComfy CLI downloads approved output URLs into the selected output directory.
What data leaves my computer?
The prompt and reference image URLs are sent to RunComfy. Review sensitive content before submitting a request.
개발자 세부 정보
작성자
prime-skills라이선스
MIT
Skillstore 리비전
r1
버전 안내
작성자가 버전을 선언하지 않았습니다.
참조
c2699b3d2240ab1c1a324ff4aeca6a238369ae59
유지보수 최신성
2026. 8. 14.
사용량
0 다운로드 · 0 조회
파일 구조
📄 SKILL.md
prime-skills의 다른 스킬
전체 보기📦
image-to-video
77Animate Images with RunComfy Video Models
Different video requests require different models, media inputs, and prompt settings. This skill guides RunComfy model selection and CLI calls for animation, voiceover lip-sync, and combined references.
디자인 및 크리에이티브 보기
📦
gpt-image-edit
77Edit Images with GPT Image on RunComfy
Targeted image edits can change details you want to preserve. This skill provides RunComfy commands and focused prompts for background changes, text replacement, and reference-based composition.
디자인 및 크리에이티브 보기
📦
relight
77Relight Still Images with RunComfy
Existing photos may have lighting that does not match the desired mood or product presentation. This skill guides RunComfy relighting with model selection and precise lighting prompts.
디자인 및 크리에이티브 보기
📦
image-inpainting
70Edit Image Regions with Masks or Descriptions
Local image edits need clear targeting and preservation constraints. This skill guides RunComfy model selection and CLI requests for masked inpainting or description-based edits.
디자인 및 크리에이티브 보기
📦
video-outpainting
69Expand Video Canvases with RunComfy
Changing video formats can crop important action or leave empty borders. This skill guides prompt-driven canvas expansion through RunComfy and recommends dedicated workflows for stricter quality needs.
디자인 및 크리에이티브 보기
관련 스킬
전체 보기📦
imagegen
82Create and Edit Project Images
작성자 openai
Producing consistent raster assets requires precise prompts, careful edits, and reliable output handling. This skill structures requests, creates or edits visuals, validates results, and saves project-ready files.
디자인 및 크리에이티브 보기
📦
flux-kontext
78Flux Kontext Pro로 이미지 편집
작성자 agentspace-so
정밀한 이미지 편집에는 명확한 모델 라우팅과 집중된 프롬프트가 필요합니다. 이 스킬은 Claude, Codex, Claude Code가 RunComfy를 통해 Flux 1 Kontext Pro를 호출할 수 있도록 실용적인 프롬프트 패턴을 제공합니다.
디자인 및 크리에이티브 보기
📦
controlnet-pose
79포즈 제어 이미지 및 비디오 만들기
작성자 runcomfy-com
포즈 제어 생성에는 적절한 모델과 입력 형식을 선택해야 하는 경우가 많습니다. 이 스킬은 이미지 및 비디오 요청을 RunComfy 워크플로로 라우팅합니다.
디자인 및 크리에이티브 보기
📦
image-outpainting
79프레임 너머로 이미지 확장
작성자 agentspace-so
크롭된 이미지는 배너, 소셜 게시물 또는 제품 레이아웃을 위해 더 넓은 캔버스가 필요한 경우가 많습니다. 이 스킬은 원본 피사체를 보존하면서 RunComfy 모델로 이미지를 아웃페인팅하도록 Claude, Codex, Claude Code를 안내합니다.
디자인 및 크리에이티브 보기
📦
native-transparent-imagegen
86Generate Native-Alpha Transparent Images
작성자 zseven-w
Image generators can return opaque files or painted checkerboards when transparency is required. This skill generates native-alpha assets and validates every untouched output.
디자인 및 크리에이티브 보기
📦
sketchbook-style
84Create Industrial Design Sketchbook Images
작성자 keith-cy
Generic image prompts often produce polished illustrations instead of quick industrial design sketches. This skill combines four style variants, rendering settings, ink post-processing, and measurements for more consistent sketchbook pages.
디자인 및 크리에이티브 보기