ClawHub
Back to skill

Security audit

TikTok Shop 电商图片生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

This is a purpose-aligned TikTok Shop image-generation skill that uses AI Hive, uploads user-selected media, and stores an API key locally without evidence of hidden or destructive behavior.

Install only if you are comfortable sending selected product images and prompts to AI Hive and storing or providing an AI Hive API key. Use the documented generate/task/init flow and avoid uploading files that are unrelated or sensitive.

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 exposes operational capabilities including shell, network, file read/write, and environment access without declaring permissions or constraining them in the manifest. That creates a transparency and trust boundary problem: a user invoking an image-generation skill may unknowingly trigger broader code execution and external communication than the description suggests.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The documented purpose is narrow, but the implementation reportedly supports much broader actions including multimodal chat, video generation, account and wallet retrieval, model discovery, generic media upload, and credential initialization/storage. This mismatch is dangerous because it expands the attack surface and can mislead users and reviewers about what data the skill can access, what side effects it can cause, and whether sensitive credentials or account metadata may be handled.

Static analysis

No suspicious patterns detected.