ClawHub

Nanobanana Pro

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it says: generate or edit images through Google's Gemini API and save the result locally.

Before installing, confirm you are comfortable sending prompts and any selected input images to Google's Gemini service, and save outputs to a dedicated folder or unique filenames to avoid accidental overwrites.

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 (3)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The README instructs users to supply a Gemini API key and send prompts/images to a cloud image-generation API, but it does not clearly disclose that user text and uploaded images will be transmitted to an external third-party service. In an agent-skill context, this omission can cause users to unknowingly expose sensitive prompts or local images, especially because the skill supports multi-image uploads and presents itself as 'Zero Config,' which reduces friction and may lower user caution.

Missing User Warnings

Low
Confidence
82% confidence
Finding
The documented commands write image files to user-specified paths, but the skill does not warn that existing files may be overwritten or that output locations should be chosen carefully. In practice this can cause accidental data loss or unintended modification of user files, especially when an agent constructs filenames automatically.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs use of Gemini Image API with prompts and input images, but it does not disclose that those prompts and images are sent to an external third-party service. This creates a real privacy and data-handling risk because users may provide sensitive text or local images without understanding they will leave the local environment.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal