ClawHub
Back to skill

Security audit

Nano Banana 2 海报生成

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent poster image-generation helper that clearly uses a fixed AI Hive API, user-provided images, and a locally stored API key.

Before installing, understand that this skill will send prompts and any reference images you explicitly provide to AI Hive, and it can store an AI Hive API key locally if you run init. Use only approved images and keep the local key file protected.

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
95% confidence
Finding
The skill invokes a local Python script with shell commands, can read and write files, uses environment variables, and sends requests over the network, but it does not declare corresponding permissions. This creates a trust and review gap: users and policy controls may not realize the skill can access local data, persist secrets, and make outbound requests, which increases the chance of unintended data exposure or misuse.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.