Is johanesalxd/vision-sandbox safe?

https://github.com/openclaw/skills/tree/main/skills/johanesalxd/vision-sandbox

98
SAFE

Vision Sandbox is a legitimate image analysis tool that uses Google's Gemini API for spatial grounding and visual reasoning tasks. The code is clean with no malicious behavior detected, though users should be aware that images are sent to Google's servers as part of normal operation.

Category Scores

Prompt Injection 100/100 · 30%
Data Exfiltration 95/100 · 25%
Code Execution 100/100 · 20%
Clone Behavior 100/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 95/100 · 5%

Findings (1)

LOW Images sent to external API -5 ▶

The skill sends user images to Google's Gemini API for analysis. While this is the documented and intended functionality, users should be aware that images will be transmitted to Google's servers.