Vision Helper — AI Image Analysis

Analyze images using local or cloud vision models via Ollama to identify content, UI elements, screenshots, or extract text with OCR support.

This skill appears to be what it claims: a helper that reads an image file and sends it to an Ollama instance for analysis. Before installing or using it, consider the following: - Privacy: The script will read any readable file with an allowed extension and base64-encode it. If you take desktop/browser screenshots you may capture passwords, private chats, or other sensitive data. - Endpoint trust: By default the script posts to http://localhost:11434/api/chat. If you change OLLAMA_API_URL to a remote URL, those images (and any textual prompt) will be transmitted to that remote service. Only point it to endpoints you trust. - File validation is extension-based and the path-traversal check is simplistic ('..' substring). Don't feed files you don't trust; avoid symlink/renamed files containing sensitive content. - Automation caution: The README suggests using model output to drive clicks or inputs; make sure any automation steps are safe and tested before running with real privileges or on critical systems. Practical steps: run a local Ollama instance and keep OLLAMA_API_URL at its default if you want privacy; inspect or run the included script in a sandbox first; avoid passing images containing secrets; and do not set OLLAMA_API_URL to an external service unless you control or trust it.

Type: OpenClaw Skill Name: vision-helper Version: 1.0.0 The vision-helper skill is a utility designed to analyze images via Ollama, specifically addressing timeout limitations in built-in tools. The core script (scripts/analyze_image.py) is well-structured, using standard Python libraries and implementing security best practices such as path traversal checks and file extension validation. No evidence of data exfiltration, malicious execution, or obfuscation was found; the skill functions transparently as a wrapper for vision model APIs.