ClawHub
Back to skill

Security audit

Nano Banana Pro

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it says: generate or edit images through Google Gemini, with normal privacy caution for prompts and images sent to Google.

Install only if you are comfortable sending prompts and any selected input images to Google Gemini and using your Gemini API quota. Prefer GEMINI_API_KEY in the environment instead of passing the key on the command line, avoid sensitive images unless your policy allows third-party processing, and review uv-resolved dependencies if supply-chain controls matter.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
When input images are provided, the script sends them to Google's external Gemini image API as part of the request, but it does not clearly warn the user at the point of use that local files will be transmitted off-host. This can lead to unintentional disclosure of sensitive images, especially in agent or automation contexts where users may not realize that local content is being uploaded to a third party.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.