Skills ai-image-generation

📦

ai-image-generation

Name: ai-image-generation
Author: doany-ai

Content revision r1 Medium Risk ⚙️ External commands🌐 Network access📁 Filesystem access

Generate Images with RunComfy Models

Choosing the right image model is hard when each endpoint has different strengths. This skill routes Claude, Codex, or Claude Code requests to suitable RunComfy image workflows.

Supports: Claude Codex Code(CC)

📊 69 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "ai-image-generation" from https://skillstore.io/skills/doany-ai-ai-image-generation.md and its manifest at https://skillstore.io/api/skills/doany-ai-ai-image-generation/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

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.

Markdown detail GET /skills/doany-ai-ai-image-generation.md Signed manifest GET /api/skills/doany-ai-ai-image-generation/manifest Signed lockfile GET /api/skills/doany-ai-ai-image-generation/lockfile

Test it

Using "ai-image-generation". Create a product photo of a ceramic mug on a marble counter.

Expected outcome:

The skill selects a fast product-image route and produces a warm, clean product composition in the output folder.

Using "ai-image-generation". Make a poster with the exact headline AURORA Spring 2026.

Expected outcome:

The skill chooses a typography-focused route and returns a poster image with the requested headline and layout.

Using "ai-image-generation". Use this portrait URL and change only the background.

Expected outcome:

The skill selects an image-edit route and preserves the subject while generating the requested new background.

Security Audit

Medium Risk

v4 • 7/5/2026 Open versioned report

Most static findings are false positives caused by Markdown backticks, documentation links, placeholder URLs, and model-selection wording. The real risks are intended RunComfy CLI execution, remote processing of prompts and reference images, and npm/npx setup guidance. No prompt-injection attempt was found in the skill text.

Files scanned

497

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (3)

Medium

SKILL.md:4 SKILL.md:42-44 SKILL.md:475

Third-Party Prompt and Image Processing

The skill grants Bash(runcomfy *) and states that the CLI POSTs requests to RunComfy. Prompts and reference image URLs can leave the local environment for remote processing.

The allowed-tools declaration and How it works section directly show RunComfy CLI execution and remote API posting. This is intended behavior, but it is a real data-boundary risk.

Low

SKILL.md:31-34 SKILL.md:51-52 SKILL.md:479

External Package Installation Guidance

The documentation shows npm and npx setup commands for the RunComfy CLI and skill installation. This creates a supply-chain consideration if an agent treats setup examples as executable workflow steps.

The install commands are visible in setup documentation, and line 479 frames them as operator setup. The skill later limits executable scope, so the risk is low rather than high.

Low

SKILL.md:482-485

Untrusted Reference Content Can Steer Outputs

The skill notes that reference image URLs and web-search results are untrusted. Remote content can influence generated outputs through embedded text or grounding data.

The security section explicitly identifies reference URLs and web-search results as untrusted inputs. The skill includes mitigations, so this is an integrity caution rather than malicious intent.

Risk Factors

⚙️ External commands (122)

SKILL.md:6 SKILL.md:15 SKILL.md:25 SKILL.md:31-45 SKILL.md:45-51 SKILL.md:51-53 SKILL.md:53-61 SKILL.md:61-66 SKILL.md:66-71 SKILL.md:71 SKILL.md:76-81 SKILL.md:81-82 SKILL.md:82-86 SKILL.md:86-91 SKILL.md:91-96 SKILL.md:96-101 SKILL.md:101-106 SKILL.md:106-107 SKILL.md:107-111 SKILL.md:111 SKILL.md:116-117 SKILL.md:117-123 SKILL.md:123-128 SKILL.md:128-131 SKILL.md:131-133 SKILL.md:133-136 SKILL.md:136-138 SKILL.md:138-143 SKILL.md:143-148 SKILL.md:148-153 SKILL.md:153-158 SKILL.md:158-163 SKILL.md:163-168 SKILL.md:168-174 SKILL.md:174 SKILL.md:181-182 SKILL.md:182-183 SKILL.md:183-184 SKILL.md:184-192 SKILL.md:192-201 SKILL.md:201-205 SKILL.md:205-209 SKILL.md:209-216 SKILL.md:216-222 SKILL.md:222-229 SKILL.md:229 SKILL.md:230 SKILL.md:236-243 SKILL.md:243-247 SKILL.md:247-254 SKILL.md:254-258 SKILL.md:258-259 SKILL.md:259 SKILL.md:260 SKILL.md:267-268 SKILL.md:268-274 SKILL.md:274-275 SKILL.md:275-276 SKILL.md:276-277 SKILL.md:277 SKILL.md:278 SKILL.md:279 SKILL.md:280-281 SKILL.md:281-287 SKILL.md:287-291 SKILL.md:291-295 SKILL.md:295-304 SKILL.md:304-309 SKILL.md:309-310 SKILL.md:310 SKILL.md:316 SKILL.md:317-321 SKILL.md:321-325 SKILL.md:325-344 SKILL.md:344 SKILL.md:345 SKILL.md:346 SKILL.md:347 SKILL.md:348 SKILL.md:356-360 SKILL.md:360-367 SKILL.md:367-369 SKILL.md:369 SKILL.md:373-381 SKILL.md:381-383 SKILL.md:383 SKILL.md:387-394 SKILL.md:394-396 SKILL.md:396 SKILL.md:404 SKILL.md:405 SKILL.md:406 SKILL.md:407 SKILL.md:408 SKILL.md:409 SKILL.md:411-418 SKILL.md:418-419 SKILL.md:419-422 SKILL.md:422-425 SKILL.md:425 SKILL.md:431 SKILL.md:446-447 SKILL.md:447-448 SKILL.md:448-449 SKILL.md:449-450 SKILL.md:450-451 SKILL.md:451-452 SKILL.md:452-475 SKILL.md:475 SKILL.md:479 SKILL.md:480 SKILL.md:481 SKILL.md:482-485 SKILL.md:485 SKILL.md:486 SKILL.md:488 SKILL.md:492-493 SKILL.md:493-494 SKILL.md:494-495 SKILL.md:495-496 SKILL.md:481 SKILL.md:481

🌐 Network access (51)

📁 Filesystem access (5)

SKILL.md:364 SKILL.md:377 SKILL.md:391 SKILL.md:480 SKILL.md:480

Audited by: codex View Audit History →

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.

Open versioned report

Copy report link

https://skillstore.io/skills/doany-ai-ai-image-generation/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/doany-ai-ai-image-generation.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 · BibTeX · CFF)

APA citation

doany-ai. (2026). ai-image-generation security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/doany-ai-ai-image-generation/audits/4

BibTeX citation

@techreport{doany-ai-doany-ai-ai-image-generation-2026,
  author = {doany-ai},
  title = {ai-image-generation security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/doany-ai-ai-image-generation/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: "ai-image-generation 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-ai-image-generation/audits/4"
identifiers:
  - type: other
    value: "skillstore:doany-ai-ai-image-generation:audit:4"
    description: "Skillstore immutable audit report identifier"

Compare variants

23 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Higher Skillstore usage

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

tool-belt Recommended

tool-belt-ai-image-generation

Skillstore Score 78

Evidence Confidence High

Skillstore usage 25

Updated

2026-08-21

runcomfy-com

runcomfy-com-ai-image-generation

Skillstore Score 78

Evidence Confidence High

Skillstore usage 22

Updated

2026-08-21

inference-shell

inference-shell-ai-image-generation

Skillstore Score 78

Evidence Confidence High

Skillstore usage 11

Updated

2026-08-21

tul-sh

tul-sh-ai-image-generation

Skillstore Score 75

Evidence Confidence High

Skillstore usage 19

Updated

2026-08-21

inferen-sh

inferen-sh-ai-image-generation

Skillstore Score 69

Evidence Confidence High

Skillstore usage 15

Updated

2026-08-21

infsh-skills

infsh-skills-ai-image-generation

Skillstore Score 69

Evidence Confidence High

Skillstore usage 11

Updated

2026-08-21

inference-skills

inference-skills-ai-image-generation

Skillstore Score 69

Evidence Confidence High

Skillstore usage 10

Updated

2026-08-21

inference-sh

inference-sh-skills-ai-image-generation

Skillstore Score 69

Evidence Confidence High

Skillstore usage 8

Updated

2026-08-21

skillssh

skillssh-ai-image-generation

Skillstore Score 69

Evidence Confidence High

Skillstore usage 7

Updated

2026-08-21

doany-ai Current

doany-ai-ai-image-generation

Skillstore Score 69

Evidence Confidence High

Skillstore usage 6

Updated

2026-08-21

qu-skills

qu-skills-ai-image-generation

Skillstore Score 69

Evidence Confidence Medium

Skillstore usage 12

Updated

2026-08-21

genmedia-labs

genmedia-labs-ai-image-generation

Skillstore Score 69

Evidence Confidence Medium

Skillstore usage 2

Updated

2026-08-21

toolshell

toolshell-ai-image-generation

Skillstore Score 50

Evidence Confidence High

Skillstore usage 15

Updated

2026-08-21

skills-shell

skills-shell-ai-image-generation

Skillstore Score 50

Evidence Confidence High

Skillstore usage 7

Updated

2026-08-21

101-skills

101-skills-ai-image-generation

Skillstore Score 50

Evidence Confidence Medium

Skillstore usage 6

Updated

2026-08-21

prime-skills

prime-skills-ai-image-generation

Skillstore Score 50

Evidence Confidence Medium

Skillstore usage 2

Updated

2026-08-21

agentspace-so

agentspace-so-ai-image-generation

Skillstore Score 38

Evidence Confidence High

Skillstore usage 13

Updated

2026-08-21

halt-catch-fire

halt-catch-fire-ai-image-generation

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 50

Updated

2026-08-21

inference-sh

inference-sh-ai-image-generation

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 32

Updated

2026-08-21

inference-sh-9

inference-sh-9-ai-image-generation

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 19

Updated

2026-08-21

inference-sh-8

inference-sh-8-ai-image-generation

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-08-21

skills-collective

skills-collective-ai-image-generation

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 5

Updated

2026-08-21

danielgwilson

danielgwilson-ai-image-generation

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 4

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Create Campaign Visuals

Generate posters, hero images, and multilingual creatives with model guidance for text accuracy and layout control.

Explore Product Concepts

Produce fast moodboards, product shots, and style variants before selecting a final image route.

Automate Image Workflows

Use consistent RunComfy CLI patterns for repeatable generation and edit tasks in agent workflows.

Try These Prompts

Generate a Simple Image

Generate a square image of [subject]. Use [style] and [lighting]. Choose the best RunComfy model and save the result locally.

Create Text in an Image

Create a landscape poster for [brand]. The headline must read exactly "[text]". Pick a model that handles typography well.

Edit a Reference Image

Edit this reference image: [URL]. Keep [protected elements] unchanged. Change only [requested change] and explain the selected route.

Plan a Multi-Model Workflow

Plan an image workflow for [project]. Compare speed, text accuracy, photorealism, and open-weight needs. Then generate the first production image.

Best Practices

State the subject, style, lighting, size, and any exact text before asking for generation.
Use user-provided reference URLs only, and describe what each reference should control.
Keep web search disabled unless real-world grounding is required and explicitly requested.

Avoid

Do not send private images, secrets, or confidential text unless the user accepts remote processing.
Do not request arbitrary image sizes for models that publish fixed size choices.
Do not use this skill for mask-driven inpainting when a dedicated edit skill is required.

Frequently Asked Questions

What does this skill use to create images?

It uses the RunComfy CLI to call hosted image generation and edit models.

Does it work with Claude, Codex, and Claude Code?

Yes. The report lists support for Claude, Codex, and Claude Code.

Can it edit an existing image?

Yes. It supports image-to-image routes when the user provides reference image URLs.

Can it create images with exact text?

Yes. It recommends typography-focused routes for posters, labels, and multilingual text.

Where are results saved?

RunComfy downloads generated results into the chosen local output directory.

What should users avoid sharing?

Users should avoid confidential prompts, private image URLs, credentials, and regulated data.

Developer Details

Author

doany-ai

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/doany-ai/skills/tree/main/ai-image-generation/

Ref

c579efd02184f1128d6741d16e6c8d951d7d4208

Maintenance freshness

7/18/2026

Usage

4 downloads · 0 views

File structure

Create MaxArt Prompt Packs

by jerrylearner187

Creative teams often have strong ideas but lack consistent prompts, variations, and production notes. This skill turns a brief or reference asset into organized MaxArt-ready image and video direction.

Design & Creative View

ai-image-generation

Install with my Agent

Agent-readable resources

Test it

Security Audit

Confirmed security concerns (3)

Risk Factors

Copy report link

Markdown badge

HTML badge

Embed card

APA citation

BibTeX citation

CITATION.cff

Compare variants

Skillstore Score

What You Can Build

Create Campaign Visuals

Explore Product Concepts

Automate Image Workflows

Try These Prompts

Best Practices

Avoid

Frequently Asked Questions

Developer Details

More from doany-ai

controlnet-pose

runcomfy-cli

elevenlabs-music-generation

ai-video-generation

ace-step

seedance-v2

Related Skills

imagegen

image-outpainting

generating-storyboards

generating-ai-actors

qwen-image-2-pro

maxart-creative-studio