← Back to Skills Marketplace
425
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install product-image-generator
Description
Generates professional product images for e-commerce platforms (Amazon, Shopify, eBay, etc.). Supports 8 visual styles and 6 scene types optimized for differ...
Usage Guidance
This skill's docs and presets look legitimate for producing e‑commerce images, but important runtime details are missing. Before installing or running it: 1) Ask the author what actually generates the PNGs (local binary, local image model, or an external API) and whether any network calls will be made; 2) Confirm the exact filesystem paths it will read/write and whether you are comfortable allowing writes to $HOME/.teamclaw-skills/ and your project directory; 3) If the skill needs an external image API or binary, require the author to declare that and any credential requirements; 4) Run first in an isolated/test environment (or sandbox) so it cannot unexpectedly modify other files; 5) If you accept it, review the created EXTEND.md and generated prompts to ensure no sensitive information is being recorded or transmitted.
Capability Analysis
Type: OpenClaw Skill
Name: product-image-generator
Version: 1.0.0
The skill is classified as suspicious due to the presence of a shell command (`test -f`) directly embedded in `SKILL.md`, which represents a potential shell injection vulnerability if the AI agent executes markdown content without proper sandboxing. Additionally, the `--ref <path>` option allows user-controlled file paths to be incorporated into prompts for the image generation model, posing a prompt injection vulnerability against the model itself. While these do not show clear evidence of intentional malicious behavior (e.g., data exfiltration or system compromise), they are risky capabilities and vulnerabilities that could be exploited.
Capability Assessment
Purpose & Capability
Name/description and the large set of documentation files are coherent for an image‑generation/creative workflow. However, the skill claims to 'generate images' but provides no code, no install, and no explicit image generation backend (no API calls, no model, no included binary). The SKILL.md examples call a /product-image-generator executable and show generated image files, but that binary or any image engine is not part of the package — this gap should be justified by the author (e.g., requires a separate image generator or platform service).
Instruction Scope
Runtime instructions reference reading and writing preferences (EXTEND.md) at both project (.teamclaw-skills/) and user ($HOME/.teamclaw-skills/...) paths, instruct the agent to run a local '/product-image-generator' command, and assume the ability to create files under product-images/. The skill metadata declared no required config paths, but the instructions clearly touch the user's filesystem. The SKILL.md is also vague about the actual image generation step (which tool/API to call), leaving broad discretionary behavior to the agent.
Install Mechanism
There is no install spec and no code to download or execute from external URLs, which reduces supply‑chain risk. Because it's instruction-only, nothing in the manifest will automatically be written to disk by an installer. The remaining risk is runtime: the instructions expect a binary or external tool to exist.
Credentials
The skill requests no environment variables or credentials (good). However, it expects to save and load preference files at project and user locations (e.g., $HOME/.teamclaw-skills/product-image-generator/EXTEND.md) without those paths being declared in metadata; this grants the skill write access to the user's home directory which should be considered before use.
Persistence & Privilege
always:false and no special privileges are requested. The skill will persist user preferences in its own config files (EXTEND.md) if the agent follows the instructions — that is a normal behavior for a user‑level tool and not an elevated privilege.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install product-image-generator - After installation, invoke the skill by name or use
/product-image-generator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of product-image-generator — generate e-commerce product images with style, scene, and platform optimization.
- Supports 8 visual styles and 6 scene types for diverse e-commerce product photography needs.
- Auto-selects visual settings based on product category, with options for manual override.
- Adapts image specifications for Amazon, Shopify, eBay, Etsy, Taobao, JD, and Pinduoduo.
- Guidance for scenario-based product image strategies (product-focused, lifestyle-focused, information-focused).
- Generates images, prompts, and outlines in a structured session directory, with product slugging and conflict resolution.
- Step-by-step guided workflow with confirmation checkpoints and progress tracking.
Metadata
Frequently Asked Questions
What is Product Image Generator?
Generates professional product images for e-commerce platforms (Amazon, Shopify, eBay, etc.). Supports 8 visual styles and 6 scene types optimized for differ... It is an AI Agent Skill for Claude Code / OpenClaw, with 425 downloads so far.
How do I install Product Image Generator?
Run "/install product-image-generator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Product Image Generator free?
Yes, Product Image Generator is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Product Image Generator support?
Product Image Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Product Image Generator?
It is built and maintained by Yang Jun (@boyd4y); the current version is v1.0.0.
More Skills