Image2Prompt
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill coherently analyzes user-provided images to create image-generation prompts, with expected use of OpenClaw/OpenAI and no evidence of hidden code, persistence, destructive actions, or deceptive behavior.
This skill appears benign and purpose-aligned. Before installing or using it, make sure you are comfortable sending selected images to the configured OpenAI/OpenClaw provider, especially portraits or confidential product/screenshots, and use a dedicated API key if possible.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Using the skill may consume OpenAI account quota or incur API costs through the configured key.
The skill expects access to an OpenAI API key, which gives the agent delegated ability to use the user's provider account for image analysis.
Primary credential: OPENAI_API_KEY
Use a dedicated or restricted API key where possible, monitor usage, and avoid sharing the key in prompts or files.
Private images, portraits, product photos, or screenshots may be exposed to the configured model service during analysis.
The documented workflow sends a user-selected image through OpenClaw for model analysis. This is expected for the skill, but it means image contents may be processed outside the local environment depending on the configured provider.
openclaw message send --image /path/to/image.jpg "Analyze this image and generate a detailed prompt for reproduction"
Only submit images you are comfortable processing with the configured provider, and review provider privacy and retention settings for sensitive images.