Nano Banana Pro

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it generates or edits images with Google Gemini, with normal cautions about API-key use and sending prompts/images to Google.

Install only if you are comfortable sending the prompt and any selected input images to Google Gemini and using your Gemini API quota. Prefer a dedicated or limited API key stored in the environment rather than passed on the command line, avoid sensitive images unless allowed by your data policy, and review uv-resolved Python dependencies if supply-chain control matters.

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
92% confidence
Finding
The script transmits the user’s prompt and any supplied input images to Google’s external Gemini API, but it does not provide an explicit privacy or data-transmission warning at the point of use. In an agent-skill context, users may reasonably assume local processing, so sensitive prompts or images could be unintentionally disclosed to a third party.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal