← 返回 Skills 市场
bluestar-34

Minimax Image Gen

作者 Neuroblue · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ⚠ suspicious
283
总下载
0
收藏
5
当前安装
1
版本数
在 OpenClaw 中安装
/install minimax-image-gen
功能描述
使用 Minimax Image API 生成图片。支持文生图、13+ 种风格预设、跨平台。 neuroXY 专属画图技能! Use when: 用户想生成图片、AI 画图、创建图像。 NOT for: 视频生成、动画制作。
安全使用建议
This skill appears to do what it claims (generate images via Minimax) and only requires MINIMAX_API_KEY, but there are two things to check before installing or running it: 1) SSL verification is disabled in the script when calling the API and downloading images (ssl.check_hostname=False; verify_mode=ssl.CERT_NONE). That means an attacker on your network could intercept requests and steal your API key or responses. If you plan to use this skill, either run it only on trusted networks or edit the script to remove the lines that disable certificate verification so TLS is enforced. 2) The script will try to read ~/.openclaw/openclaw.json (and a parent-path variant) to auto-load an API key. If that file contains other credentials, the script will open it while searching for a Minimax key. To minimize risk, prefer supplying MINIMAX_API_KEY via an explicit environment variable and inspect/remove any sensitive keys from the config file first. Other suggestions: review the full script locally before running, confirm the base_url (https://api.minimaxi.com) matches the official endpoint you expect, and run in a contained environment if you are not comfortable modifying the code. If the SSL disabling is fixed and you supply the key via env only, the skill would be coherent and lower-risk.
功能分析
Type: OpenClaw Skill Name: minimax-image-gen Version: 1.1.0 The skill contains a significant security vulnerability by explicitly disabling SSL/TLS certificate verification (ssl.CERT_NONE) in scripts/gen.py during both API communication and image downloads. It also accesses the user's home directory to read a global configuration file (~/.openclaw/openclaw.json) to retrieve API keys. While these behaviors appear aimed at user convenience and avoiding environment-specific certificate issues, they introduce MITM risks and perform unauthorized file access outside the skill's scope.
能力评估
Purpose & Capability
Name, description, SKILL.md, and the included script all align: the tool calls a Minimax image-generation API, accepts prompts/presets, and saves/previews images. Required binary (python3) and required env var (MINIMAX_API_KEY) match the stated purpose.
Instruction Scope
The SKILL.md and script instruct reading an API key from env or from ~/.openclaw/openclaw.json (documented in SKILL.md). That's reasonable, but the runtime code explicitly disables SSL certificate verification for both the API POST and image downloads (ssl.check_hostname=False; verify_mode=ssl.CERT_NONE). This weakens transport security and could expose the API key or image data to MitM attacks. The script also attempts to read OpenClaw config files in home and parent paths — this is described in SKILL.md but means the skill will try to access local config files that may contain other credentials.
Install Mechanism
No install spec (instruction-only skill) and included Python script; nothing is downloaded or executed from arbitrary URLs during install. Standard library modules are used. Low installation risk, but runtime network activity occurs (to api.minimaxi.com).
Credentials
The skill only requires MINIMAX_API_KEY (declared as primary credential), which is proportionate. However, the code will also attempt to extract an API key from ~/.openclaw/openclaw.json and a sibling path; if that file contains other provider credentials, the skill will read them while searching for a Minimax key. This behavior is documented but increases the risk surface compared with using only an explicit env var.
Persistence & Privilege
always is false and the skill does not request persistent elevated privileges or modify other skills. It does not self-enable or write system-wide config beyond creating output files in the specified output directory.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install minimax-image-gen
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /minimax-image-gen 触发
  4. 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
v1.1.0
minimax-image-gen v1.1.0 introduces major feature updates and improvements: - Added 13 built-in style presets for image generation. - Introduced style type options (e.g., 漫画/元气/中世纪/水彩) for more creative outputs. - Improved cross-platform compatibility for Windows, macOS, and Linux. - Enhanced security features, including better API key handling and encrypted transmission. - Expanded and refined documentation for usage, configuration, and troubleshooting.
元数据
Slug minimax-image-gen
版本 1.1.0
许可证 MIT-0
累计安装 6
当前安装数 5
历史版本数 1
常见问题

Minimax Image Gen 是什么?

使用 Minimax Image API 生成图片。支持文生图、13+ 种风格预设、跨平台。 neuroXY 专属画图技能! Use when: 用户想生成图片、AI 画图、创建图像。 NOT for: 视频生成、动画制作。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 283 次。

如何安装 Minimax Image Gen?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install minimax-image-gen」即可一键安装,无需额外配置。

Minimax Image Gen 是免费的吗?

是的,Minimax Image Gen 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Minimax Image Gen 支持哪些平台?

Minimax 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 Minimax Image Gen?

由 Neuroblue(@bluestar-34)开发并维护,当前版本 v1.1.0。

💬 留言讨论