← 返回 Skills 市场
apifox-image-gen
作者
balckbeeai
· GitHub ↗
· v1.0.0
· MIT-0
254
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install apifox-image-gen
功能描述
使用Apifox图像生成API (jyapi.AI-WX.CN) 生成图片。支持gpt-image-1.5和grok-4-1-image模型。
使用说明 (SKILL.md)
Apifox Image Generation
使用jyapi.AI-WX.CN图像生成API生成图片。
快速开始
python3 /root/.openclaw/workspace/skills/apifox-image-gen/image_gen.py -p "你的图片描述" -m gpt-image-1.5 -s 1024x1024
参数说明
| 参数 | 简写 | 默认值 | 说明 |
|---|---|---|---|
| --prompt | -p | (必填) | 图片描述 |
| --model | -m | gpt-image-1.5 | 模型: gpt-image-1.5, grok-4-1-image |
| --size | -s | 1024x1024 | 尺寸: 1024x1024, 1536x1024, 1024x1536, 1:1, 2:3, 3:2, 9:16, 16:9 |
| --n | -n | 1 | 生成数量 |
| --output | -o | (自动) | 输出文件路径 |
示例
# 生成小蜜蜂图片
python3 /root/.openclaw/workspace/skills/apifox-image-gen/image_gen.py -p "一只可爱的小蜜蜂" -m gpt-image-1.5 -s 1024x1024
# 生成横版图片
python3 /root/.openclaw/workspace/skills/apifox-image-gen/image_gen.py -p "风景画" -m gpt-image-1.5 -s 1536x1024
# 生成竖版图片
python3 /root/.openclaw/workspace/skills/apifox-image-gen/image_gen.py -p "手机壁纸" -m gpt-image-1.5 -s 9:16
# 使用grok模型
python3 /root/.openclaw/workspace/skills/apifox-image-gen/image_gen.py -p "科技感海报" -m grok-4-1-image -s 16:9
使用方式
- 直接用exec运行脚本
- 图片会保存到 /tmp/ 目录
- 可以用message工具发给用户
安全使用建议
This skill implements image generation as advertised, but it embeds an API key directly in the script and points at an external domain (jyapi.AI-WX.CN). Before installing or running it: (1) don't use it with any sensitive data; run it in a sandbox; (2) assume the embedded API key is someone else's — it may be revoked, abused, or billable; prefer replacing the hard-coded key with your own key provided via an environment variable; (3) verify the API endpoint and the account owner (jyapi.AI-WX.CN) and review terms/billing; (4) if you published this or rely on it, rotate the exposed key immediately and update the code to read credentials from secure config or env vars. If you cannot confirm the key/endpoint, treat this skill as untrusted.
功能分析
Type: OpenClaw Skill
Name: apifox-image-gen
Version: 1.0.0
The skill contains a hardcoded API key in `image_gen.py` and relies on a third-party API proxy (jyapi.AI-WX.CN). It is classified as suspicious due to security vulnerabilities: the hardcoded credential and the use of `urllib.request.urlretrieve` on external API responses, which could potentially be exploited for local file access (SSRF/Local File Read) if the API returns a malicious file URI.
能力评估
Purpose & Capability
The SKILL.md and image_gen.py both implement an image-generation client for the described jyapi.AI-WX.CN service and support the named models; the functionality implemented (POST /v1/images/generations, download image, save to /tmp) is coherent with the description.
Instruction Scope
Instructions only tell the agent to exec the included script and then send images via message. The script performs network calls to the specified API and downloads generated images to /tmp. The instructions do not mention the embedded API key or billing/account implications; they also reference an absolute workspace path (/root/.openclaw/...) which assumes a specific runtime layout.
Install Mechanism
No install spec is present (instruction-only skill with a single Python script). Nothing is automatically downloaded or executed beyond the included file.
Credentials
The code contains a hard-coded API key (API_KEY = "sk-...") and a BASE_URL for jyapi.AI-WX.CN, yet requires.env lists none. Embedding a secret in the code is disproportionate and risky: a legitimate skill would typically accept a user-provided API key via environment variable or config. The hard-coded key may be a leaked/third-party credential and could result in unexpected billing or abuse. The skill requests no other credentials, but the single embedded secret is a major red flag.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system-wide settings, and has no install steps that grant persistent elevated privileges.
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 apifox-image-gen - 安装完成后，直接呼叫该 Skill 的名称或使用
/apifox-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 of apifox-image-gen:
- Provides image generation via the jyapi.AI-WX.CN API.
- Supports gpt-image-1.5 and grok-4-1-image models.
- Allows customization of image description, model, size, quantity, and output path.
- Includes command-line script for easy usage and sample commands.
- Generated images are saved to the /tmp/ directory.
元数据
常见问题
apifox-image-gen 是什么？
使用Apifox图像生成API (jyapi.AI-WX.CN) 生成图片。支持gpt-image-1.5和grok-4-1-image模型。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 254 次。
如何安装 apifox-image-gen？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install apifox-image-gen」即可一键安装，无需额外配置。
apifox-image-gen 是免费的吗？
是的，apifox-image-gen 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
apifox-image-gen 支持哪些平台？
apifox-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 apifox-image-gen？
由 balckbeeai（@darker314159）开发并维护，当前版本 v1.0.0。
推荐 Skills