← 返回 Skills 市场

Draw Images By Apiyi

Name: Draw Images By Apiyi
Author: mengwuzhi

作者 mengwuzhi · GitHub ↗ · v1.0.0

cross-platform ⚠ suspicious

416

总下载

当前安装

版本数

在 OpenClaw 中安装

/install draw-images-by-apiyi

功能描述

Generate images using APIYI API.

使用说明 (SKILL.md)

Draw Images by APIYI

Generate images using APIYI API. Simple and fast.

Usage

Slash Command (Recommended)

/draw-images-by-apiyi a cute cat wearing sunglasses
/draw-images-by-apiyi a sunset over mountains -r 2K

Natural Language

Just ask the agent:

"Draw a cute cat for me"
"Generate an image of a sunset"
"Can you create a picture of a robot?"

Command Line

uv run {baseDir}/scripts/generate_image.py --prompt "your image description" --filename "output.png"

Examples

Basic generation

uv run {baseDir}/scripts/generate_image.py -p "a cute cat wearing sunglasses" -f cat.png

With resolution

uv run {baseDir}/scripts/generate_image.py -p "a sunset over mountains" -f sunset.png -r 2K

With explicit API key

uv run {baseDir}/scripts/generate_image.py -p "a robot" -f robot.png --api-key YOUR_API_KEY

API Key

Get your API key from https://apiyi.com/

Set via environment:

export APIYI_API_KEY=your-key-here

Or configure in ~/.openclaw/openclaw.json:

{
  skills: {
    entries: {
      "draw-images-by-apiyi": {
        enabled: true,
        env: {
          "APIYI_API_KEY": "your-key-here"
        }
      }
    }
  }
}

Parameters

Parameter	Values	Default	Description
`--prompt`, `-p`	text	required	Image description
`--filename`, `-f`	path	required	Output filename
`--resolution`, `-r`	`1K`, `2K`, `4K`	`1K`	Output resolution
`--api-key`, `-k`	string	env var	Override environment variable

Output Path

Relative path (e.g., -f out.png) → outputs to current workspace root
Absolute path (e.g., -f /tmp/out.png) → uses specified path

Notes

Resolutions: 1K (1024×1024), 2K (2048×2048), 4K (4096×4096)
The script prints a MEDIA: line for OpenClaw to auto-attach images
Requires APIYI_API_KEY environment variable

安全使用建议

This skill appears coherent, but review these practical points before installing: 1) Trust the API provider (https://apiyi.com) — the skill will send your prompts and API key to that service; use an API key with limited scope if possible. 2) The script downloads an image from a URL returned by the service and writes files to the workspace or any absolute path you specify — avoid giving absolute paths you don't trust. 3) The skill requires the 'uv' runtime (installed via Homebrew) and will pull Python dependencies (openai, requests, pillow) when run; verify those packages and the uv formula are acceptable in your environment. 4) Keep your API key secret (do not paste it into public places); the skill accepts the key via env var or CLI arg. 5) If you do not want the agent to call this skill autonomously, control invocation or disable it in your agent settings.

功能分析

Type: OpenClaw Skill Name: draw-images-by-apiyi Version: 1.0.0 The skill allows writing images to arbitrary absolute paths specified by the `--filename` argument in `scripts/generate_image.py`, as documented in `SKILL.md`. While this functionality might be intended for flexibility, it introduces an arbitrary file write vulnerability. An AI agent, if compromised or maliciously prompted, could be instructed to overwrite or create files in sensitive system locations, potentially leading to denial of service, privilege escalation, or other system compromise. There is no evidence of intentional malicious behavior by the skill itself, but this capability poses a significant security risk.

能力评估

✓ Purpose & Capability

Name/description ask to generate images via APIYI and the skill only requires the APIYI_API_KEY and the 'uv' runtime used to run the included Python script. No unrelated credentials or binaries are requested.

✓ Instruction Scope

SKILL.md and the Python script limit actions to contacting APIYI, downloading the returned image URL, saving the image to the specified path, and printing a MEDIA: line for attachment. There are no instructions to read unrelated files, enumerate system secrets, or transmit data to other endpoints.

✓ Install Mechanism

Install uses a Homebrew formula ('uv') which is an expected low-risk mechanism for providing the required runtime. The skill does not download arbitrary archives or run obscure installers. Python dependencies are declared in the script comments (likely managed by the uv runtime).

✓ Credentials

Only APIYI_API_KEY is required and is declared as the primary credential. The script also accepts an --api-key override. No other secrets or unrelated environment variables are requested.

✓ Persistence & Privilege

The skill is not always-enabled and is user-invocable. It does not request permanent presence, nor does it modify other skills or system-wide settings.

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 draw-images-by-apiyi
安装完成后，直接呼叫该 Skill 的名称或使用 /draw-images-by-apiyi 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 draw-images-by-apiyi skill. - Generate images using the APIYI API via slash command, natural language, or command line. - Supports customizable prompts, resolutions (1K, 2K, 4K), and API key management. - Output images can be saved to relative or absolute paths. - Includes detailed usage instructions and configuration options for API keys.

元数据

Slug draw-images-by-apiyi

版本 1.0.0

许可证 —

累计安装 2

当前安装数 2

历史版本数 1

常见问题