Skills qwen-image-2
๐Ÿ“ฆ

qwen-image-2

Content revision r2 Medium Risk โš™๏ธ External commands๐ŸŒ Network access

Create and Edit Images with Qwen-Image-2

Creating polished images and text-heavy graphics often requires several tools. This skill runs Qwen-Image-2 models through inference.sh for generation, editing, and controlled output.

Supports: Claude Codex Code(CC)
๐Ÿ“Š 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 "qwen-image-2" from https://skillstore.io/skills/inferen-sh-qwen-image-2.md and its manifest at https://skillstore.io/api/skills/inferen-sh-qwen-image-2/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-2". Create four minimalist coffee shop logo concepts with dark green lettering and simple cup shapes.

Expected outcome:

Four PNG logo concepts with consistent minimalist styling, distinct cup symbols, and dark green typography.

Using "qwen-image-2". Design a vertical summer sale poster with exact headline and subtitle text.

Expected outcome:

A 1024 by 1536 poster with the requested headline, subtitle, beach background, and clear text placement.

Using "qwen-image-2". Combine an authorized person, clothing, and pose reference into one edited image.

Expected outcome:

One PNG image preserving the selected person while applying the requested clothing and pose references.

Security Audit

Medium Risk
v5 โ€ข 8/6/2026 Open versioned report

Most static alerts are false positives caused by Markdown backticks, fixed CLI examples, public links, and an image parameter name. The unpinned npx skill installations are genuine supply-chain risks, and reference-image editing sends user data to an external processor.

1
Files scanned
187
Lines analyzed
2
Review items
0
False positives ignored

Confirmed security concerns (1)

Medium
Reference Images Are Sent to an External Service
The editing workflow submits reference-image URLs through inference.sh model execution. Sensitive or access-controlled images could be disclosed to the external processor.
The example explicitly places three image URLs in reference_images for a belt app run. External processing is the stated function, although service retention is not documented here.
Capability review items (2)

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
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
This command invokes an unpinned npx package to install a separate community skill. Executing mutable third-party installer content creates a supply-chain risk.
Medium
Ruby/shell backtick execution
```bash
These npx commands install several external skills without versions or immutable revisions. Their future contents can change and execute with the agent's granted capabilities.
Audited by: codex View Audit History โ†’
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
Security Assessment

Copy report link

https://skillstore.io/skills/inferen-sh-qwen-image-2/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/inferen-sh-qwen-image-2/security.svg)](https://skillstore.io/skills/inferen-sh-qwen-image-2?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/inferen-sh-qwen-image-2?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inferen-sh-qwen-image-2/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/inferen-sh-qwen-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>
Academic citations (APA ยท BibTeX ยท CFF)

APA citation

inferen-sh. (2026). qwen-image-2 security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inferen-sh-qwen-image-2/audits/5

BibTeX citation

@techreport{inferen-sh-inferen-sh-qwen-image-2-2026, author = {inferen-sh}, title = {qwen-image-2 security audit report (audit version 5)}, institution = {Skillstore}, year = {2026}, number = {5}, url = {https://skillstore.io/skills/inferen-sh-qwen-image-2/audits/5}, 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-2 security audit report (audit version 5)" version: "unspecified" type: report authors: - name: "inferen-sh" date-released: "2026-08-06" url: "https://skillstore.io/skills/inferen-sh-qwen-image-2/audits/5" identifiers: - type: other value: "skillstore:inferen-sh-qwen-image-2:audit:5" description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

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

Why this variant is first

Highest Skillstore Score
inference-shell Recommended

inference-shell-qwen-image-2

Skillstore Score 77
Evidence Confidence High
Skillstore usage 10
Updated

2026-08-21

inferen-sh Current

inferen-sh-qwen-image-2

Skillstore Score 69
Evidence Confidence High
Skillstore usage 10
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

Create Campaign Graphics

Generate posters with specified headlines, colors, layouts, and dimensions using the Pro model.

Produce Concept Variations

Generate several visual directions from one prompt for rapid comparison and refinement.

Edit Reference Images

Combine subject, clothing, and pose references into a new image through multi-reference editing.

Try These Prompts

Generate a Basic Image
Create an image of [subject] in [style] with [lighting]. Use Qwen-Image-2.0 and return one image.
Create Several Concepts
Generate [number] variations of [concept]. Use [width] by [height] pixels and avoid [unwanted details].
Design a Text-Heavy Poster
Use Qwen-Image-2.0-Pro to design a [format] poster. Include the exact text "[copy]" with [typography and placement].
Combine Multiple References
Edit these authorized reference images: [URLs]. Preserve [elements], combine [attributes], use seed [seed], and describe the final composition before running.

Best Practices

  • Use the Pro model for posters, labels, and other text-heavy designs.
  • Place required visible text in quotes and specify its color, style, and position.
  • Use a fixed seed when comparing prompt changes or reproducing an approved result.

Avoid

  • Do not submit confidential images or private URLs without authorization.
  • Do not request dimensions outside the documented limits.
  • Do not rely on generated text without checking spelling, layout, and legibility.

Frequently Asked Questions

What is required before using this skill?
Install the belt CLI, authenticate with inference.sh, and ensure network access is available.
Which model should I use?
Use Qwen-Image-2.0 for general speed. Use the Pro model for posters, detailed realism, and important text.
Can it edit existing images?
Yes. Provide one to three authorized reference-image URLs and describe how their elements should be combined.
Can I generate repeatable results?
Use the same prompt, model, settings, and seed. External model updates can still affect exact output.
How many images can one request create?
The documented num_images setting supports one to six images.
How should sensitive images be handled?
Do not submit confidential material unless you understand and accept the external service's privacy and retention terms.

Developer Details

Author

inferen-sh

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Ref

4121de961d1b6f2ffca856260e239505c302452c

Maintenance freshness

8/7/2026

Usage

9 downloads ยท 145 views

File structure

๐Ÿ“„ SKILL.md