← Back to Skills Marketplace
410
Downloads
0
Stars
2
Active Installs
1
Versions
Install in OpenClaw
/install wan-text2image
Description
阿里云DashScope Wan2.6文生图工具。使用阿里云百炼平台的Wan2.6-t2i模型生成图片。 当用户需要：AI生成图片、文生图、从文字生成图像时触发。 需要DASHSCOPE_API_KEY环境变量（已在系统中配置）。
Usage Guidance
This skill appears to do what it says: send prompts to Aliyun DashScope and return generation results. Before installing, verify that you are comfortable sending prompt text to dashscope.aliyuncs.com and that the DASHSCOPE_API_KEY you provide has appropriate scope and billing limits. Note the registry metadata currently omits the required DASHSCOPE_API_KEY—treat that as a metadata bug and confirm the key requirement with the publisher. As best practice, use a dedicated API key with minimal privileges, monitor usage/billing, and rotate/revoke the key if you stop using the skill.
Capability Analysis
Type: OpenClaw Skill
Name: wan-text2image
Version: 1.0.0
The script `scripts/t2i.sh` is vulnerable to command injection because it expands shell variables ($PROMPT, $NEGATIVE_PROMPT, $SIZE) directly inside a double-quoted string passed to curl. This allows an attacker to execute arbitrary commands on the host system via crafted input. While the script correctly targets the official Alibaba DashScope API (dashscope.aliyuncs.com) and lacks clear evidence of malicious intent, the critical security flaw warrants a suspicious classification.
Capability Assessment
Purpose & Capability
The name/description, SKILL.md, and the shell script all describe calling Aliyun DashScope's wan2.6-t2i model. The script posts the prompt/negative_prompt/size to the endpoint and uses an Authorization bearer token as expected. Minor naming inconsistency: SKILL.md and script refer to 'wan-t2i' while the registry slug is 'wan-text2image' (likely cosmetic).
Instruction Scope
Runtime instructions are limited to invoking the included script (or curl) to call the stated API. The script only reads its command-line args and the DASHSCOPE_API_KEY environment variable; it does not read other files, scan the system, or transmit data to unexpected endpoints.
Install Mechanism
No install specification — the skill is instruction/script-only. The single included shell script is short and readable; nothing is downloaded or written to disk by an install step.
Credentials
The SKILL.md and script require DASHSCOPE_API_KEY (used as a Bearer token for the API), which is proportional to the stated purpose. However, the registry metadata lists 'Required env vars: none', creating an inconsistency that should be corrected before trusting the metadata.
Persistence & Privilege
The skill does not request always:true and has no install-time persistence or configuration changes. It does not attempt to modify other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install wan-text2image - After installation, invoke the skill by name or use
/wan-text2image - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of wan-t2i skill.
- Provides text-to-image generation using Aliyun DashScope Wan2.6-t2i model.
- Supports prompt and negative prompt inputs; allows custom image sizes.
- Requires DASHSCOPE_API_KEY (already configured) and curl.
- Offers shell script interface with clear parameter options.
- Chinese prompts are recommended for optimal results.
Metadata
Frequently Asked Questions
What is wan-text2image?
阿里云DashScope Wan2.6文生图工具。使用阿里云百炼平台的Wan2.6-t2i模型生成图片。 当用户需要：AI生成图片、文生图、从文字生成图像时触发。 需要DASHSCOPE_API_KEY环境变量（已在系统中配置）。 It is an AI Agent Skill for Claude Code / OpenClaw, with 410 downloads so far.
How do I install wan-text2image?
Run "/install wan-text2image" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is wan-text2image free?
Yes, wan-text2image is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does wan-text2image support?
wan-text2image is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created wan-text2image?
It is built and maintained by baokui (@baokui); the current version is v1.0.0.
More Skills