Skills ai-image-generation

📦

ai-image-generation

Name: ai-image-generation
Author: skills-shell

Content revision r1 Medium Risk ⚙️ External commands🌐 Network access

Generate AI Images with Inference.sh

Image teams often compare many generators, prompts, and edit tools. This skill gives Claude, Codex, and Claude Code guided belt workflows for image creation and refinement.

Supports: Claude Codex Code(CC)

⚠️ 50 Poor

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/skills-shell-ai-image-generation.md and its manifest at https://skillstore.io/api/skills/skills-shell-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/skills-shell-ai-image-generation.md Signed manifest GET /api/skills/skills-shell-ai-image-generation/manifest Signed lockfile GET /api/skills/skills-shell-ai-image-generation/lockfile

Test it

Using "ai-image-generation". A user asks for a studio image of sneakers for a product page.

Expected outcome:

The skill recommends a product-focused model, frames a concise prompt, and describes a belt run that returns an image file or hosted result.

Using "ai-image-generation". A user provides an image URL and asks for a sunset beach background.

Expected outcome:

The skill selects an editing model, keeps the main subject unchanged, and reminds the user that the source image is sent externally.

Using "ai-image-generation". A user has two generated images and wants one banner.

Expected outcome:

The skill suggests the stitch images app, asks for the image URLs, and describes a horizontal composition workflow.

Security Audit

Medium Risk

v6 • 7/9/2026 Open versioned report

The static Ruby backtick and hardcoded URL findings are mostly Markdown false positives, and I found no hidden executable code in SKILL.md. The remaining concerns are contextual: broad belt CLI permission, unpinned remote skill installation guidance, and user content being sent to external image services.

Files scanned

172

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (3)

Medium

SKILL.md:4

Broad Belt CLI Permission Surface

The frontmatter permits Bash(belt *), so the assistant may invoke any belt subcommand. This is broader than the documented image workflow and can allow unintended account, file, or network operations through the CLI.

The broad tool permission is explicit in the skill frontmatter. The exact impact depends on the installed belt CLI subcommands, so the confidence is high but not critical.

Medium

SKILL.md:7 SKILL.md:138-162

Unpinned Remote Skill Installation Guidance

The skill recommends npx skills add for belt-sh/cli and several inference-sh/skills entries without pinning reviewed versions. Users who follow it may install remote skill content that changes after review.

The install guidance is directly visible in the cited lines and uses remote skill identifiers without versions. This creates a clear supply-chain concern, even though it is user-facing documentation.

Low

SKILL.md:58-124

External Image Service Data Disclosure

The examples send prompts and image URLs to external model apps through belt, but the skill does not place a privacy warning next to those workflows. This can expose sensitive prompts or images if users provide them.

The examples clearly invoke external image model apps with prompts and image URLs. The finding is limited to disclosure because the external service use is the stated purpose of the skill.

Risk Factors

⚙️ External commands (44)

🌐 Network access (9)

SKILL.md:11 SKILL.md:13 SKILL.md:17 SKILL.md:70 SKILL.md:124 SKILL.md:131 SKILL.md:168 SKILL.md:169 SKILL.md:170

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/skills-shell-ai-image-generation/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/skills-shell-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

skills-shell. (2026). ai-image-generation security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/skills-shell-ai-image-generation/audits/6

BibTeX citation

@techreport{skills-shell-skills-shell-ai-image-generation-2026,
  author = {skills-shell},
  title = {ai-image-generation security audit report (audit version 6)},
  institution = {Skillstore},
  year = {2026},
  number = {6},
  url = {https://skillstore.io/skills/skills-shell-ai-image-generation/audits/6},
  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 6)"
version: "unspecified"
type: report
authors:
  - name: "skills-shell"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/skills-shell-ai-image-generation/audits/6"
identifiers:
  - type: other
    value: "skillstore:skills-shell-ai-image-generation:audit:6"
    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

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 Current

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 Product Mockups

Generate studio-style product images and refine backgrounds before a campaign review.

Explore Concept Art

Compare model choices for characters, environments, posters, and illustration styles.

Prepare Image Assets

Upscale, edit, or stitch image URLs for documentation, presentations, and social posts.

Try These Prompts

Generate A First Image

Use ai-image-generation to create a product image of a matte black water bottle on a white studio background. Choose a suitable model and explain the next step.

Choose A Model

Use ai-image-generation to compare GPT-Image-2, FLUX, Gemini, and Seedream for a detailed poster with readable text. Recommend one model and explain why.

Edit An Existing Image

Use ai-image-generation to change the background of this image URL to a warm office scene. Keep the product unchanged and mention any privacy considerations.

Build A Campaign Workflow

Use ai-image-generation to plan a workflow for three social ads. Include model choice, prompt direction, editing, upscaling, and final asset review.

Best Practices

Confirm that prompts and image URLs do not contain confidential or sensitive material.
Choose the model based on output goal, such as text rendering, cost, editing, or resolution.
Record prompts, model names, and settings so successful results can be reproduced.

Avoid

Do not send private customer images or unreleased product photos without approval.
Do not assume every model supports editing, LoRA, upscaling, or exact text rendering.
Do not install related skills or CLI tools from unpinned sources in restricted environments.

Frequently Asked Questions

Does this skill generate images itself?

No. It guides an AI assistant to use the external inference.sh belt CLI and supported model apps.

Which tools can use it?

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

Do I need an inference.sh account?

Yes. The quick start requires the belt CLI and login before generation.

Can it edit existing images?

Yes. The examples show image editing with a prompt and a source image URL.

Can it upscale images?

Yes. The skill includes a Topaz image upscaler example through belt.

Is it safe for sensitive images?

Use caution. Prompts and image URLs are sent to external inference services selected in the workflow.

Developer Details

Author

skills-shell

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

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

Ref

0519034dad657fb1f7706e0550e962beeda73fdf

Maintenance freshness

7/18/2026

Usage

5 downloads · 45 views

File structure

📄 SKILL.md