📦
qwen-image
74Generate Qwen Images with inference.sh
Image teams need fast Qwen-Image prompts without writing API calls. This skill turns natural language requests into inference.sh image generation and editing runs.
Design & Creative View
Skills qwen-image-pro
📦
qwen-image-pro
Content revision r1 Medium Risk ⚙️ External commands🌐 Network access
Generate Qwen Image Pro Designs
Text-heavy AI images can lose clear lettering and layout detail. This skill guides Claude, Codex, or Claude Code to use Qwen-Image-2.0-Pro for polished images.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "qwen-image-pro" from https://skillstore.io/skills/toolshell-qwen-image-pro.md and its manifest at https://skillstore.io/api/skills/toolshell-qwen-image-pro/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.
Test it
Using "qwen-image-pro". Create a launch poster with the headline "New Season" and a clean editorial layout.
Expected outcome:
A PNG poster concept with the requested headline, modern layout, and dimensions noted in the result metadata.
Using "qwen-image-pro". Generate four banner variations for a coffee shop called Bean and Brew.
Expected outcome:
Four image options with consistent branding direction, different compositions, and clear headline treatment.
Using "qwen-image-pro". Use two image references to place an outfit from one image onto the person in another image.
Expected outcome:
Two edited PNG options that combine the requested subject and outfit references.
Security Audit
Medium Riskv7 • 7/7/2026 Open versioned report
Most static findings are false positives caused by Markdown code fences, inline parameter names, and documentation links. I found no prompt-injection attempt or hidden execution logic, but the skill does use a broad infsh CLI permission and sends image prompts or references to an external service.
1
Files scanned
206
Lines analyzed
0
Review items
0
False positives ignored
Confirmed security concerns (2)
Medium
Broad External CLI Permission
The skill grants Bash access to any infsh subcommand with the allowed-tools pattern Bash(infsh *). This is broader than the documented Qwen image workflow and increases impact if prompt guidance is abused.
The allowed-tools declaration is explicit, and examples show infsh commands for app sample and app run. The concern is scope expansion, not evidence of malicious intent.
Low
Third-Party Image Processing Disclosure Needed
The skill sends prompts and reference image locations to inference.sh for remote image generation. Users may expose confidential text, image URLs, or creative assets unless the skill warns them clearly.
The skill states that it uses inference.sh and includes reference image URI inputs. This confirms external processing, but it appears to be disclosed core functionality rather than covert exfiltration.
Risk Factors
⚙️ External commands (39)
SKILL.md:15 SKILL.md:17-21 SKILL.md:21-35 SKILL.md:35-39 SKILL.md:39-43 SKILL.md:43-50 SKILL.md:50-54 SKILL.md:54-62 SKILL.md:62-66 SKILL.md:66-71 SKILL.md:71-75 SKILL.md:75-84 SKILL.md:84-88 SKILL.md:88-93 SKILL.md:93-99 SKILL.md:99-100 SKILL.md:100-101 SKILL.md:101-102 SKILL.md:102-103 SKILL.md:103-104 SKILL.md:104-105 SKILL.md:105-106 SKILL.md:106-107 SKILL.md:107-115 SKILL.md:115-116 SKILL.md:116-122 SKILL.md:122-124 SKILL.md:124-125 SKILL.md:125-128 SKILL.md:128-133 SKILL.md:133-137 SKILL.md:137-141 SKILL.md:141-145 SKILL.md:145-152 SKILL.md:152-156 SKILL.md:156-184 SKILL.md:184-188 SKILL.md:188-197 SKILL.md:197-199
🌐 Network access (7)
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.
Copy report link
https://skillstore.io/skills/toolshell-qwen-image-pro/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/toolshell-qwen-image-pro?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/toolshell-qwen-image-pro?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/toolshell-qwen-image-pro/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/toolshell-qwen-image-pro.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
toolshell. (2026). qwen-image-pro security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/toolshell-qwen-image-pro/audits/7BibTeX citation
@techreport{toolshell-toolshell-qwen-image-pro-2026,
author = {toolshell},
title = {qwen-image-pro security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/toolshell-qwen-image-pro/audits/7},
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: "qwen-image-pro security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
- name: "toolshell"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/toolshell-qwen-image-pro/audits/7"
identifiers:
- type: other
value: "skillstore:toolshell-qwen-image-pro:audit:7"
description: "Skillstore immutable audit report identifier"
Compare variants
2 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
tul-sh Recommended
tul-sh-qwen-image-pro
Skillstore Score 70
Evidence Confidence High
Skillstore usage 18
Updated
2026-08-21
toolshell Current
toolshell-qwen-image-pro
Skillstore Score 69
Evidence Confidence High
Skillstore usage 17
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: High 55
Architecture
85
Maintainability
87
Content
69
Community
83
Spec Compliance
What You Can Build
Design marketing posters
Create posters and sale graphics with clear quoted headlines, layout instructions, and controlled dimensions.
Prepare product visuals
Generate product photography concepts, campaign images, or banner variations for online stores.
Edit reference images
Combine person and outfit references or test style transfer with one to three input images.
Try These Prompts
Create a Simple Poster
Use qwen-image-pro to generate one 1024 by 1024 poster. Text: "Grand Opening". Style: clean, modern, blue and white.
Make Banner Variations
Generate four 1920 by 1080 marketing banner variations for a summer sale. Keep the headline "SUMMER SALE" clear and centered.
Edit With References
Use two reference images. Keep the person from image one, apply the outfit from image two, and return two polished options.
Control Reproducible Text
Generate a 1024 by 1536 event poster with seed 12345, prompt extension disabled, exact quoted title, font placement, and a negative prompt for blurry text.
Best Practices
- Put exact text in quotes and describe placement, font style, size, and color.
- Disable prompt extension when precise wording or layout matters.
- Avoid sensitive images or confidential text because processing uses an external service.
Avoid
- Sending private client images without permission or a data handling review.
- Combining many unrelated creative directions in one prompt.
- Publishing generated text without checking spelling, spacing, and layout.
Frequently Asked Questions
What model does this skill use?
It uses Alibaba Qwen-Image-2.0-Pro through the inference.sh CLI.
Do I need an inference.sh account?
Yes. The documented workflow requires the infsh CLI to be installed and authenticated.
Can it edit existing images?
Yes. The skill documents reference image URI inputs for image editing and style transfer workflows.
Is text rendering always exact?
No. Quoted text, font details, negative prompts, and disabled prompt extension can improve results.
Does it send data to an external service?
Yes. Prompts and reference image URLs are processed through inference.sh and the image model provider.
Which AI tools can use this skill?
The report lists support for Claude, Codex, and Claude Code.
Developer Details
Author
toolshellLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
36e07d5e13068e5be64447e8f20b427cf2cbd21a
Maintenance freshness
7/18/2026
Usage
11 downloads · 131 views
File structure
📄 SKILL.md
More from toolshell
View all📦
nano-banana-2
70Generate Gemini Images with Nano Banana 2
Image generation workflows need clear model settings and repeatable prompts. This skill helps Claude, Codex, and Claude Code use Gemini image generation through inference.sh.
Design & Creative View
📦
remotion-render
69Render Remotion Videos from React Code
Programmatic video work often needs a reliable way to turn React animation code into finished files. This skill guides Claude, Codex, and Claude Code through rendering Remotion components with inference.sh.
Design & Creative View
📦
ai-video-generation
50Generate AI Videos with Inference.sh
Video teams need quick access to many AI video models. This skill provides CLI examples for text-to-video, image animation, lipsync, upscaling, foley, and merging.
Design & Creative View
📦
ai-image-generation
50Generate AI Images with inference.sh
Teams need fast access to image models without memorizing app IDs. This skill provides ready prompts and CLI patterns for generation, editing, upscaling, and stitching.
Design & Creative View
📦
nano-banana
50Create Gemini Images with Nano Banana
Image generation often requires switching tools and assembling CLI options. This skill gives Claude, Codex, and Claude Code concise commands for Gemini image creation, editing, and grounded image prompts.
Design & Creative View
Related Skills
View all📦
qwen-image-2-pro
79Generate Text-Rich Images with Qwen Pro
by inference-shell
Design teams need image prompts that preserve text and layout details. This skill guides Claude, Codex, or Claude Code to call Qwen-Image-2-Pro through inference.sh.
Design & Creative View
📦
generating-storyboards
82Create Consistent Video Storyboards
by supercmohq
Video concepts can lose continuity when clips are planned separately. This skill creates sequential storyboard sheets that preserve characters, products, settings, and visual states.
Design & Creative View
📦
generating-ai-actors
82Create Reusable Photorealistic AI Actors
by supercmohq
Campaign teams need consistent fictional talent without supplying a person photograph. This skill creates one detailed adult identity that can guide later image and video generation.
Design & Creative View
📦
imagegen
82Create and Edit Project Images
by 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.
Design & Creative View
📦
controlnet-pose
79Create Pose-Controlled Images and Videos
by doany-ai
Pose and motion control workflows can be hard to route across image and video models. This skill selects the right RunComfy path and prepares clear CLI guidance.
Design & Creative View
📦
maxart-creative-studio
79Create 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