← 返回 Skills 市场
500
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install phoenixclaw-image-gen
功能描述
图像生成辅助。支持通过 OpenRouter 直接调用各种生图模型（如 Seedream），为 OpenClaw 优化，支持提示词、尺寸等参数配置。目前仅限 OpenRouter provider。
功能分析
Type: OpenClaw Skill
Name: phoenixclaw-image-gen
Version: 0.2.1
The skill bundle is classified as suspicious due to a critical data exfiltration vulnerability in `scripts/generate.js`. The `generateImageWithRetry` function reads the `inputImagePath` argument using `fs.readFileSync` without any path validation, allowing an attacker to specify arbitrary local file paths (e.g., `--input-image /etc/passwd`). The content of these files is then base64 encoded and sent to the OpenRouter API (`https://openrouter.ai/api/v1/chat/completions`) as part of the image generation request. While OpenRouter is a legitimate service, sending arbitrary system files to an external endpoint without explicit user consent or clear purpose constitutes a significant data exfiltration risk, stemming from a lack of input sanitization.
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 phoenixclaw-image-gen - 安装完成后，直接呼叫该 Skill 的名称或使用
/phoenixclaw-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
v0.2.1
- Added a new resolution and aspect ratio guide at references/resolution-guide.md.
- Updated recommended usage: the --size parameter now only accepts "1K", "2K", or "4K" (not pixel values).
- Documented the allowed --size values, the actual pixel outputs, supported aspect ratios, and model/resolution restrictions.
- Clarified that some models do not support 4K, and 2K is the recommended daily setting.
- Improved parameter documentation for size and aspect to align with OpenRouter API limitations.
v0.2.0
- 新增对图生图（Image-to-Image）模型的支持，默认使用 `google/gemini-2.5-flash-image`
- 支持通过环境变量分别配置文本生图与图生图模型（`IMAGE_GEN_TEXT_TO_IMAGE_MODEL`, `IMAGE_GEN_IMAGE_TO_IMAGE_MODEL`）
- 文档更新，详细说明不同模型配置与调用命令
- 参数说明和调用方式同步支持 text-to-image 与 image-to-image，提升灵活性
v0.0.2
- Added support for configuring the OpenRouter API key and default model via ~/.openclaw/openclaw.json, following OpenClaw best practices.
- Introduced optional environment variable IMAGE_GEN_DEFAULT_MODEL for customizable default model selection.
- Provided instructions for listing all available models and choosing/recommending different model IDs.
- Updated documentation to clarify new configuration methods; removed shell profile setup guidance in favor of OpenClaw config file.
- No breaking changes to CLI or workflow.
v0.0.1
- Initial release of the image-generation skill for OpenClaw.
- Enables high-quality image generation via OpenRouter using prompt, model, size, and aspect ratio parameters.
- Default model is bytedance-seed/seedream-4.5; only OpenRouter is supported as provider.
- API key required; auto-configures environment variables for user.
- Includes CLI scripts for image generation, connectivity check, and clear exit codes for errors.
- Designed for integration with OpenClaw’s workflow and safety standards.
元数据
常见问题
phoenixclaw image gen 是什么？
图像生成辅助。支持通过 OpenRouter 直接调用各种生图模型（如 Seedream），为 OpenClaw 优化，支持提示词、尺寸等参数配置。目前仅限 OpenRouter provider。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 500 次。
如何安装 phoenixclaw image gen？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install phoenixclaw-image-gen」即可一键安装，无需额外配置。
phoenixclaw image gen 是免费的吗？
是的，phoenixclaw image gen 完全免费（开源免费），可自由下载、安装和使用。
phoenixclaw image gen 支持哪些平台？
phoenixclaw 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 phoenixclaw image gen？
由 betterest（@goforu）开发并维护，当前版本 v0.2.1。
推荐 Skills