← 返回 Skills 市场
Azure Image Gen
作者
abhibavishi
· GitHub ↗
· v1.0.0
742
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install azure-image-gen
功能描述
Generate images using Azure OpenAI DALL-E. Supports batch generation, custom prompts, and outputs a gallery.
使用说明 (SKILL.md)
Azure Image Gen
Generate images using Azure OpenAI's DALL-E deployment.
Setup
Required Environment Variables
export AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com"
export AZURE_OPENAI_API_KEY="your-api-key"
export AZURE_OPENAI_DALLE_DEPLOYMENT="your-dalle-deployment-name"
Or create a .env file in the skill directory.
API Version
Default: 2024-02-01 (supports DALL-E 3)
Usage
Basic Generation
python3 /Users/abhi/clawd/skills/azure-image-gen/scripts/generate.py --prompt "A futuristic city at sunset"
Multiple Images
python3 /Users/abhi/clawd/skills/azure-image-gen/scripts/generate.py \
--prompt "Professional blog header for a tech startup" \
--count 4
Custom Size & Quality
python3 /Users/abhi/clawd/skills/azure-image-gen/scripts/generate.py \
--prompt "Minimalist illustration of cloud computing" \
--size 1792x1024 \
--quality hd
Specify Output Directory
python3 /Users/abhi/clawd/skills/azure-image-gen/scripts/generate.py \
--prompt "Abstract data visualization" \
--out-dir ./blog-images
Options
| Flag | Default | Description |
|---|---|---|
--prompt |
Required | Image description |
--count |
1 | Number of images to generate |
--size |
1024x1024 | Image size: 1024x1024, 1792x1024, 1024x1792 |
--quality |
standard | Quality: standard or hd |
--style |
vivid | Style: vivid or natural |
--out-dir |
./azure-images | Output directory |
--api-version |
2024-02-01 | Azure OpenAI API version |
Output
- PNG images saved to output directory
manifest.jsonwith prompt-to-file mappingindex.htmlgallery for easy preview
Blog Image Prompts
For blog headers, try prompts like:
# Tech/SaaS
"Minimalist isometric illustration of cloud migration, blue and white color scheme, clean lines, professional"
# Comparison posts
"Split screen illustration showing old vs new technology, warm vs cool colors, modern flat design"
# How-to guides
"Clean illustration of a step-by-step process, numbered steps floating in space, soft gradients"
# Cost/pricing
"Abstract visualization of savings and growth, upward arrows, green accents, professional business style"
Troubleshooting
401 Unauthorized: Check your AZURE_OPENAI_API_KEY
404 Not Found: Verify your AZURE_OPENAI_DALLE_DEPLOYMENT name matches exactly
Content Policy: Azure has strict content filters. Rephrase prompts that get blocked.
安全使用建议
This package appears to do what it claims (generate images via Azure OpenAI), but there are a few red flags to consider before installing:
- Metadata mismatch: The registry entry lists no required environment variables, but both SKILL.md and the script require AZURE_OPENAI_ENDPOINT, AZURE_OPENAI_API_KEY, and AZURE_OPENAI_DALLE_DEPLOYMENT. Treat the script as needing these secrets.
- Secrets handling: The script reads a .env in the skill directory and also reads environment variables. Avoid storing long‑lived or highly privileged credentials in plain .env files in shared locations. Use a least-privilege API key and rotate/revoke it if used for testing.
- Paths in README: Example commands use an absolute path (/Users/abhi/...). Update examples to your local path before running.
- Network behavior: The script will send your prompt and API key to your configured Azure OpenAI endpoint; ensure you trust that Azure resource and its billing/usage implications.
- Code review: The script is short and readable; if you are unsure, run it in a sandbox or inspect/execute it in a controlled environment first.
If you proceed: provide a dedicated Azure OpenAI key with minimal permissions, avoid committing the .env to source control, run the script in a non-privileged directory, and verify the endpoint and deployment names are correct. If uncertain about the source (homepage unknown, owner unverified), prefer testing in an isolated environment or request the publisher to correct the registry metadata to declare the required credentials.
功能分析
Type: OpenClaw Skill
Name: azure-image-gen
Version: 1.0.0
The skill bundle is designed for legitimate Azure DALL-E image generation. However, the `scripts/generate.py` file contains a Cross-Site Scripting (XSS) vulnerability in the `create_gallery_html` function, where the user-provided or API-revised prompt is embedded directly into the `index.html` without sanitization, allowing for potential script execution when the HTML file is viewed. Additionally, the `--out-dir` argument allows writing files to an arbitrary path, which could be abused for path traversal if the agent is instructed to specify a sensitive directory. These are vulnerabilities, not evidence of intentional malicious behavior by the skill itself.
能力评估
Purpose & Capability
The name/description, SKILL.md, and scripts/generate.py all describe an Azure OpenAI DALL‑E image generator — the requested network calls, outputs, and files are coherent with that purpose. However, the registry metadata claims no required environment variables or primary credential, while both the SKILL.md and the script require AZURE_OPENAI_ENDPOINT, AZURE_OPENAI_API_KEY, and AZURE_OPENAI_DALLE_DEPLOYMENT. This metadata omission is inconsistent and could mislead users.
Instruction Scope
SKILL.md instructs running the included Python script and only references the Azure OpenAI API and local output files (images, manifest.json, index.html). The script reads a .env located in the skill directory (Path(__file__).parent.parent / '.env') and otherwise only uses environment variables and the network to the Azure endpoint. Minor concern: SKILL.md examples use an absolute, user-specific path (/Users/abhi/...), which is non-portable and suggests the README was copied from a local environment without sanitization.
Install Mechanism
No install spec is provided and there are no downloads or extract steps — this is instruction-only with a single Python script. That reduces install-time risk; nothing in the package will be automatically fetched or executed beyond the shipped script.
Credentials
The script requires three Azure-related environment variables (endpoint, API key, deployment name) which are appropriate for the stated purpose. However, the skill metadata does not declare these requirements nor a primary credential, creating a misleading representation of required secrets. Because the skill needs an API key (sensitive secret) but the registry metadata omits this, users may not realize they must supply a credential or understand the blast radius.
Persistence & Privilege
The skill does not request permanent inclusion (always: false) and does not modify other skills or system-wide settings. It writes generated images and a manifest/index.html to a user-specified output directory only, which is expected behavior for this functionality.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install azure-image-gen - 安装完成后，直接呼叫该 Skill 的名称或使用
/azure-image-gen触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release: Azure OpenAI DALL-E image generation with batch support and HTML gallery output
元数据
常见问题
Azure Image Gen 是什么？
Generate images using Azure OpenAI DALL-E. Supports batch generation, custom prompts, and outputs a gallery. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 742 次。
如何安装 Azure Image Gen？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install azure-image-gen」即可一键安装，无需额外配置。
Azure Image Gen 是免费的吗？
是的，Azure Image Gen 完全免费（开源免费），可自由下载、安装和使用。
Azure Image Gen 支持哪些平台？
Azure Image Gen 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Azure Image Gen？
由 abhibavishi（@abhibavishi）开发并维护，当前版本 v1.0.0。
推荐 Skills