ClawHub
Back to skill

Security audit

Nano Banana 商品批次精修

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed, user-run product-photo retouching helper that uploads only selected images to AI Hive and saves generated results locally.

Install only if you are comfortable sending the specific product images you name on the command line to AI Hive and storing an AI Hive API key locally. Use --preview first to inspect the prompt and source order before uploading files.

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
92% confidence
Finding
The skill instructs users to install dependencies, authenticate with an API key, read and write local configuration files, invoke local Python scripts, and perform network operations against AI Hive, yet no permissions are declared. This creates a trust and transparency gap: an agent or user may grant broader execution than expected, exposing secrets, local files, or enabling unintended network activity without explicit consent boundaries.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.