Nano Banana Image Creator

• Outcome: Pass
• Latest audit: May 28, 2026 at 11:17 AM UTC
• Version:
  1.0.0

Overview

This skill is a straightforward Gemini image generation/editing helper, but users should avoid sensitive images and prefer environment variables for API keys.

Install only if you are comfortable sending prompts and selected input images to Google's Gemini API. Use GEMINI_API_KEY instead of pasting an API key into chat or command arguments, and avoid using confidential images or output filenames that could overwrite important files.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence
• Finding: The skill clearly depends on environment access via GEMINI_API_KEY, but the metadata does not declare permissions or otherwise warn that it reads secrets from the environment. That mismatch can undermine least-privilege expectations and make secret access less transparent to users reviewing the skill.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The usage examples encourage passing --api-key on the command line, which can expose the secret through shell history, process listings, logs, or telemetry. This is a real credential-handling weakness because users may copy the example directly and unintentionally leak their API key.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill sends user prompts and potentially local input images to an external Google API, but the documentation does not warn users about this data transfer. In a tool that handles local files and creative prompts, missing disclosure can lead to unintended sharing of sensitive images, embedded metadata, or confidential prompt content.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The script transmits the user's prompt and, when provided, a local input image to Google's external API, but it does not give an explicit user-facing notice at the point of transmission about what data leaves the system. In an agent skill context, this can surprise users and cause unintended disclosure of sensitive images or prompt content, especially if the skill is invoked on private local files.

VirusTotal

66/66 vendors flagged this skill as clean.