Vision Tool

Image recognition using Ollama + qwen3.5:4b with think=False for reliable content extraction.

This skill appears to do exactly what it claims: it reads a local image file, Base64-encodes it, and POSTs it to an Ollama /api/chat endpoint on localhost. Before installing or running it, ensure you: 1) run a trusted Ollama instance locally (ollama serve) and have pulled qwen3.5:4b, 2) confirm the Ollama service is not proxying/forwarding requests to an untrusted remote endpoint (if you change the default URL the skill will send images to wherever that URL points), and 3) review and run the included tests in a safe environment. Because the skill does not request secrets or remote installs and the code is readable, there are no incoherent or disproportionate requests — but always verify you trust the Ollama server you will use (local vs remote).

Type: OpenClaw Skill Name: vision-tool Version: 1.1.3 The vision-tool skill bundle is a legitimate implementation for image recognition using a local Ollama instance. The core logic in `scripts/vision_core.py` uses the `requests` library to communicate with the Ollama API on localhost (127.0.0.1:11434) and handles image data via standard Base64 encoding. No evidence of data exfiltration, unauthorized network calls, or malicious execution was found in `main.py` or the documentation files.