← Back to Skills Marketplace
500
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install phoenixclaw-image-gen
Description
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。
Capability Analysis
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.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install phoenixclaw-image-gen - After installation, invoke the skill by name or use
/phoenixclaw-image-gen - Provide required inputs per the skill's parameter spec and get structured output
Version History
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.
Metadata
Frequently Asked Questions
What is phoenixclaw image gen?
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。 It is an AI Agent Skill for Claude Code / OpenClaw, with 500 downloads so far.
How do I install phoenixclaw image gen?
Run "/install phoenixclaw-image-gen" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is phoenixclaw image gen free?
Yes, phoenixclaw image gen is completely free (open-source). You can download, install and use it at no cost.
Which platforms does phoenixclaw image gen support?
phoenixclaw image gen is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created phoenixclaw image gen?
It is built and maintained by betterest (@goforu); the current version is v0.2.1.
More Skills