Skills gpt-image-edit
π¦
gpt-image-edit
Content revision r1 High Risk βοΈ External commandsπ Network accessπ Filesystem access
Edit Images with GPT Image 2 on RunComfy
Targeted image edits often drift, especially with faces, brands, and text. This skill provides RunComfy CLI patterns for GPT Image 2 edits with preservation-focused prompts.
Supports: Claude Codex Code(CC)
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
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.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "gpt-image-edit". A portrait needs a neutral studio background without changing the person.
Expected outcome:
A command-ready edit prompt that prioritizes face, pose, clothing, and background replacement.
Using "gpt-image-edit". A poster headline must be rewritten in Japanese while preserving the original layout.
Expected outcome:
A prompt that quotes the Japanese text and limits the edit to the headline area.
Using "gpt-image-edit". A product should be placed into a room from a second reference image.
Expected outcome:
A multi-reference prompt that identifies image 1 as the subject and image 2 as the scene.
Security Audit
High Riskv4 β’ 7/5/2026 Open versioned report
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
Files scanned
184
Lines analyzed
13
Review items
0
False positives ignored
Confirmed security concerns (2)
High
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.
Medium
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.
Capability review items (13)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Medium
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.
Medium
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.
Medium
Ruby/shell backtick execution
1. **RunComfy CLI** β `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.
Medium
Ruby/shell backtick execution
2. **RunComfy account** β `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.
Medium
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.
Medium
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.
Medium
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.
Medium
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.
Medium
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.
Low
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.
Low
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.
Low
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.
Low
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.
Risk Factors
βοΈ External commands (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
π Network access (7)
π Filesystem access (6)
Audited by: codex View Audit History β
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/doany-ai-gpt-image-edit/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/doany-ai-gpt-image-edit?utm_source=security_passport_badge)HTML badge
<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>Embed card
<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>Academic citations (APA Β· BibTeX Β· CFF)
APA citation
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 citation
@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"
Compare variants
3 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Highest Skillstore Score
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
runcomfy-com Recommended
runcomfy-com-gpt-image-edit
Skillstore Score 70
Evidence Confidence High
Skillstore usage 42
Updated
2026-09-09
agentspace-so-gpt-image-edit
Skillstore Score 50
Evidence Confidence High
Skillstore usage 10
Updated
2026-09-09
doany-ai Current
doany-ai-gpt-image-edit
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 40
Updated
2026-09-09
Skillstore Score
Why this score Evidence Confidence: Medium 55
Architecture
85
Maintainability
85
Content
67
Community
83
Spec Compliance
What You Can Build
Localize Ad Creative
Replace image headlines in another language while preserving layout, product placement, and brand marks.
Prepare Product Variants
Change backgrounds or text for a product image while keeping the main product stable.
Compose Reference Images
Combine a subject from one image with a scene or palette from other references.
Try These Prompts
Beginner Background Swap
Keep the main subject, pose, clothing, and brand marks unchanged. Replace only the background with a clean studio setting.
Localized Headline Edit
Keep the photo, layout, lighting, and logo unchanged. Replace only the headline with "Your translated text" in the same position.
Multi-Reference Composition
Use the subject from image 1 and the room style from image 2. Match lighting and preserve subject identity.
Precise Layout Revision
Keep the product and brand assets unchanged. Move the headline to the bottom center, update the CTA text, and preserve spacing.
Best Practices
- State preservation requirements before the requested change.
- Quote exact in-image text and name the script or language.
- Use size auto unless the edit requires a new aspect ratio.
Avoid
- Combining many unrelated edits into one long prompt.
- Using vague instructions such as make it better or improve the image.
- Passing private images through public URLs without approval.
Frequently Asked Questions
Does this skill generate images from scratch?
No. It focuses on editing existing images through the GPT Image 2 edit endpoint.
What tools does it support?
It is marked compatible with Claude, Codex, and Claude Code.
Do I need a RunComfy account?
Yes. The workflow requires the RunComfy CLI and authentication before model calls work.
Can it edit text inside an image?
Yes. The instructions emphasize quoting exact replacement text and preserving the surrounding layout.
How many reference images can I use?
The skill documents up to ten public HTTPS image URLs for one edit request.
Where are images processed?
Prompts and image URLs are sent to RunComfy model API endpoints for processing.