ClawHub
Back to skill

Security audit

Nano Banana 2 商品详情页

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AI Hive image-generation helper for product-detail-page visuals, with expected local key storage, explicit image uploads, polling, and downloads.

Install only if you are comfortable sending your prompts and any selected reference images to AI Hive, and storing an AI Hive API key locally in ~/.ai-hive/config.json. Use approved product assets and avoid uploading private or unauthorized images.

SkillSpector

Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill advertises shell, file, network, and environment-capable commands but declares no permissions, which creates a transparency and least-privilege failure. Users may invoke it expecting a narrow image-generation workflow while it can store keys locally, access files, and make outbound requests, increasing the chance of unintended data exposure or unsafe execution.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The documented purpose is a constrained PDP image workflow, but the described behavior expands into a more general remote image-generation tool with API-key handling, arbitrary prompt submission, uploads, task polling, and local downloads. This mismatch is dangerous because it undermines informed consent and allows broader data egress and filesystem interaction than a user would reasonably expect from the description.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.