ClawHub
Back to skill

Security audit

Nano Banana

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Gemini image generator/editor, with a credential-handling caveat users should understand before use.

Install only if you intend to use Google Gemini for image generation or editing. Prefer GEMINI_API_KEY or a secure secret workflow over passing --api-key on the command line, use a limited Gemini key where possible, and avoid sending confidential prompts or images unless you accept external processing by Google.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill documentation describes use of environment-based secrets (`GEMINI_API_KEY`) and command execution, but the metadata declares no permissions. That mismatch can cause the platform or reviewers to underestimate the skill's access to sensitive data and execution capabilities, which weakens trust boundaries and auditing. In this context, the skill is operationally capable of touching secrets from the environment, so undeclared capability is a real security issue.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The documentation explicitly recommends passing `--api-key KEY` on the command line. Command-line arguments are commonly exposed via shell history, process listings, logs, and telemetry, so this guidance can leak a live API credential to other local users or monitoring systems. Because this skill uses a paid/authenticated external API, credential exposure has direct abuse potential.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.