ClawHub
Back to skill

Security audit

Nano Banana 2 多参考图生成

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AI Hive image-generation helper that uploads user-selected reference images, stores an optional API key locally, and downloads generated results.

Install only if you are comfortable sending the reference images and prompts you choose to AI Hive, and keep the API key file private. Review image rights carefully because the skill itself instructs use of authorized people, brands, and artwork but cannot enforce authorization.

SkillSpector

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
96% confidence
Finding
The skill invokes a local Python script, performs package installation, writes API keys to disk, and sends requests to a remote API, but no declared permissions are provided to constrain or inform those capabilities. This creates a real security gap because users and enforcement systems may not realize the skill can access environment data, read/write files, execute shell commands, and make network requests.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.