ClawHub
Back to skill

Security audit

Nano Banana 2 产品图生成

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed product-image generation helper that uploads only user-specified reference images to a fixed AI Hive workflow and saves generated outputs locally.

Install only if you intend to use AI Hive for product-image generation. Treat any reference images and API key as sensitive: upload only authorized product or brand assets, and use the init command only if you are comfortable storing the key locally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill invokes a Python script that can read/write local files, access environment-derived secrets, make network requests, and execute through the shell, yet the skill declares no permissions or equivalent capability disclosure. That mismatch reduces transparency and can lead users or orchestrators to approve execution without understanding that API keys, local images, and outbound requests are involved.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The description contains very broad trigger phrases covering many generic product-image tasks and multiple commerce platforms, which can cause the skill to auto-match in more situations than necessary. Overbroad routing is risky because it may cause unintended execution of a networked script that uploads user-provided images and uses stored credentials when the user did not specifically request this skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.