ClawHub
Back to skill

Security audit

Nano Banana Pro 产品图生成

Security checks across malware telemetry and agentic risk

Overview

This is a coherent AI Hive product-image generation skill that uploads user-chosen reference images and stores an API key for later use.

Install this only if you intend to use AI Hive for product-image generation. Provide only reference images you are comfortable uploading to AI Hive, expect generated files to download under ~/Downloads/AiHive by default, and treat the stored API key in ~/.ai-hive/config.json as a paid-service credential.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill advertises only product-image generation, but the provided commands invoke a Python script with shell execution, package installation, file access, environment access, and likely networked API calls, while no permissions are declared. This creates a trust-boundary problem: users and reviewers cannot accurately assess what the skill may access or modify, increasing the risk of unexpected data exposure, filesystem changes, or command execution.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
A strong description-behavior mismatch is present: the skill is presented as a narrowly scoped product-image generator, yet static analysis indicates capabilities for chat, video generation, model enumeration, user/wallet queries, generic media upload, and browser-based API key setup. Hidden or undisclosed capabilities are dangerous because they can be used to collect sensitive user information, exfiltrate media, incur unexpected costs, or perform actions outside the user's informed consent.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The description includes many broad multilingual trigger phrases covering common e-commerce and product-image tasks, which increases the chance the skill is invoked for generic requests beyond the user's intent. Overbroad invocation matching is risky because it can route ordinary requests into a skill with powerful code, network, and file capabilities, expanding exposure unnecessarily.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.