← 返回 Skills 市场
Openai Image Gen
作者
Peter Steinberger
· GitHub ↗
· v1.0.1
26596
总下载
38
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install openai-image-gen
功能描述
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
安全使用建议
Review or patch this skill before installing. Use it only with a clean environment where OPENAI_BASE_URL and OPENAI_API_BASE are unset or intentionally trusted, avoid confidential prompts, choose an explicit --out-dir when needed, and be cautious opening or hosting the generated index.html until prompt content is escaped.
功能分析
Type: OpenClaw Skill
Name: openai-image-gen
Version: 1.0.1
The skill is benign. It generates images using the OpenAI API, requiring an `OPENAI_API_KEY` from environment variables, and saves the results along with an `index.html` gallery to a local temporary directory (`~/Projects/tmp` or `./tmp`). All network communication is directed to the OpenAI API, and file operations are confined to the designated output directory. There is no evidence of data exfiltration, malicious execution, persistence, or prompt injection attempts in the `SKILL.md` or the Python script.
能力评估
Credentials
Reading OPENAI_API_KEY is proportionate for OpenAI image generation, but reading undocumented base URL environment variables and allowing non-HTTPS or arbitrary destinations is broader than the stated OpenAI-only workflow.
Install Mechanism
No installer, package installation, remote payload retrieval, service setup, or tool replacement was present in the inspected artifact.
Instruction Scope
The instructions disclose OPENAI_API_KEY, OpenAI image generation, and output files, but they do not disclose custom endpoint routing and do not warn that custom prompts are embedded unescaped into index.html.
Persistence & Privilege
The skill does not install persistent hooks or request elevated privileges, but it creates persistent PNG, JSON, and HTML artifacts; the generated HTML can contain unescaped prompt content.
Purpose & Capability
Generating images through the OpenAI Images API is coherent with the skill purpose, but the script also honors OPENAI_BASE_URL and OPENAI_API_BASE, allowing the API key and prompts to be sent to a different endpoint without the skill instructions disclosing or validating that trust boundary.
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 openai-image-gen - 安装完成后，直接呼叫该 Skill 的名称或使用
/openai-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
v1.0.1
v1.0.0
元数据
常见问题
Openai Image Gen 是什么？
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 26596 次。
如何安装 Openai Image Gen？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openai-image-gen」即可一键安装，无需额外配置。
Openai Image Gen 是免费的吗？
是的，Openai Image Gen 完全免费（开源免费），可自由下载、安装和使用。
Openai Image Gen 支持哪些平台？
Openai 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 Openai Image Gen？
由 Peter Steinberger（@steipete）开发并维护，当前版本 v1.0.1。
推荐 Skills