ClawHub
Back to skill

Security audit

淘宝 电商视频生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent AI Hive video-generation skill that uploads user-selected media and stores an API key, with no evidence of hidden or destructive behavior.

Install this only if you are comfortable sending selected product images, video, or audio to AI Hive and storing an API key locally. Use --no-download or a controlled --output-dir when needed, and avoid uploading confidential product assets unless your AI Hive account and data handling terms permit it.

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
90% confidence
Finding
The skill advertises and demonstrates shell execution, network access, local file reads/writes, and environment-dependent behavior, yet declares no permissions. This creates a transparency and trust problem: users and review systems cannot accurately assess what the skill may access or modify, increasing the chance of unintended data exposure, filesystem changes, or unsafe command execution in agent environments.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The documented purpose is narrowly framed as Taobao/Tmall product video generation and editing, but the behavior reportedly extends to chat, image generation, account and wallet queries, model enumeration, generic media upload, browser launching, and local API key storage. This mismatch is dangerous because it obscures materially broader capabilities that can access user account data, induce credential handling, and perform actions outside the user’s expected scope.

Static analysis

No suspicious patterns detected.