Skills generate-image

📦

generate-image

Name: generate-image
Author: K-Dense-AI

Content revision r1 High Risk 🌐 Network access🔑 Env variables📁 Filesystem access⚙️ External commands

Generate AI Images with OpenRouter Models

Creating polished visual assets can be slow when users must switch tools. This skill lets Claude, Codex, and Claude Code generate or edit images through OpenRouter models from text prompts.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

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 "generate-image" from https://skillstore.io/skills/k-dense-ai-generate-image.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-generate-image/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.

Markdown detail GET /skills/k-dense-ai-generate-image.md Signed manifest GET /api/skills/k-dense-ai-generate-image/manifest Signed lockfile GET /api/skills/k-dense-ai-generate-image/lockfile

Test it

Using "generate-image". Generate a photorealistic conference poster hero image showing a modern microscopy lab.

Expected outcome:

The skill calls the selected OpenRouter image model, receives image data, and saves a PNG such as poster/hero.png.

Using "generate-image". Edit portrait.png to change the background to a soft blue studio setting.

Expected outcome:

The skill sends the image and edit prompt to the selected model, then saves the edited PNG at the requested path.

Using "generate-image". Create a scientific illustration of DNA repair with a clean editorial style.

Expected outcome:

The skill produces a general-purpose illustration suitable for slide drafts or visual concept exploration.

Security Audit

High Risk

v7 • 7/5/2026 Open versioned report

Most static findings are false positives caused by Markdown examples, JSON evaluation prose, expected OpenRouter API authentication, and normal base64 image handling. The script has a bounded confirmed filesystem risk because it writes API-returned image bytes to a caller-selected path. A high-severity semantic issue remains because evaluation.json embeds self-audit claims that could influence automated review.

Files scanned

735

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

High

evaluation.json:14-24

Prompt Injection Attempt Detected

evaluation.json embeds audit-style claims including risk_level safe, safe_to_publish true, and a claim that all static findings are false positives. This can bias an AI reviewer toward accepting author-provided safety conclusions.

The file mimics a security audit and supplies publication verdicts inside untrusted skill content. It does not contain an explicit ignore-instructions command, so confidence is high but not absolute.

Capability review items (1)

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

scripts/generate_image.py:71

Python file write/append

with open(output_path, 'wb') as f:

The script writes decoded image data to a caller-supplied output path without overwrite protection or path restriction. This is intended functionality, but it can overwrite local files if misused.

Risk Factors

🌐 Network access (10)

evaluation.json:24 evaluation.json:90 evaluation.json:90 evaluation.json:96 evaluation.json:108 scripts/generate_image.py:144 scripts/generate_image.py:111 scripts/generate_image.py:145 SKILL.md:55 SKILL.md:168

🔑 Env variables (24)

📁 Filesystem access (1)

scripts/generate_image.py:71

⚙️ External commands (39)

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/k-dense-ai-generate-image/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-generate-image.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

K-Dense-AI. (2026). generate-image security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-generate-image/audits/7

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-generate-image-2026,
  author = {K-Dense-AI},
  title = {generate-image security audit report (audit version 7)},
  institution = {Skillstore},
  year = {2026},
  number = {7},
  url = {https://skillstore.io/skills/k-dense-ai-generate-image/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: "generate-image security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
  - name: "K-Dense-AI"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/k-dense-ai-generate-image/audits/7"
identifiers:
  - type: other
    value: "skillstore:k-dense-ai-generate-image:audit:7"
    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

Higher Skillstore usage

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

K-Dense-AI Recommended Current

k-dense-ai-generate-image

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 17

Updated

2026-08-21

davila7

davila7-generate-image

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 12

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Create Research Visuals

Generate conceptual illustrations for papers, posters, and slide decks when exact schematics are not required.

Produce Presentation Assets

Create backgrounds, hero images, and visual metaphors for professional presentations and internal documents.

Iterate on Creative Concepts

Generate or revise artwork, concept images, and marketing visuals from concise creative direction.

Try These Prompts

Basic Image

Generate an image of a clean laboratory workspace with soft daylight and a professional editorial style.

Styled Asset

Generate a modern scientific illustration of immune cells attacking a tumor, with clear contrast and a publication-friendly color palette. Save it as figures/immunotherapy_concept.png.

Edit Existing Image

Edit the input image to remove background clutter, improve lighting, and keep the main subject unchanged.

Model-Specific Workflow

Use the FLUX Pro model to create three alternative poster hero concepts for a genomics workshop, each with a distinct composition and concise filename.

Best Practices

Describe the subject, composition, style, lighting, and intended use in the prompt.
Use explicit output paths and avoid overwriting important local files.
Do not send confidential images or sensitive prompts unless OpenRouter processing is acceptable.

Avoid

Do not use this skill for precise schematics, circuits, architecture diagrams, or regulated technical figures.
Do not place real API keys directly in prompts, shared notes, or committed files.
Do not assume model names, pricing, or availability remain unchanged without checking OpenRouter.