ClawHub
Back to skill

Security audit

Nano Banana 2 种草图片

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed image-generation helper that sends chosen prompts or images to AI Hive and saves results locally.

Install this only if you are comfortable sending prompts and any selected reference images to AI Hive, and storing or passing an AI Hive API key. Use authorized product/person/location assets and review advertising disclosure and platform rules before publishing generated content.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill documentation exposes executable capabilities including shell, network, filesystem access, and environment use, but does not declare permissions or constrain them in a machine-readable way. This creates a trust gap where an agent may invoke code that can read local files, write outputs, or call external services without clear user awareness or policy enforcement, increasing the risk of unintended data exposure or unsafe execution.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.