ClawHub
Back to skill

Security audit

电商爆款主图生成与编辑

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AI Hive image-generation helper for ecommerce main images, with expected API key setup, user-selected image upload, task polling, and result downloads.

Install only if you are comfortable sending selected product/reference images and prompts to AI Hive and storing an AI Hive API key locally. Use approved product assets, review platform rules before publishing, and avoid uploading confidential images unless your AI Hive account and data terms allow it.

SkillSpector

By NVIDIA
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 exposes effective capabilities for environment access, filesystem reads/writes, shell execution, and network use, yet declares no permissions. That creates a transparency and trust problem: users and platforms cannot accurately assess what the skill can do, and the combination of shell, file, and network access materially increases abuse potential if the implementation is modified or misused.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The documented purpose presents a constrained ecommerce image optimization workflow, but the actual behavior acts more like a general image-generation client with local credential storage, image upload, task polling, and local downloads. This mismatch is dangerous because users may grant trust or supply assets under narrower expectations while the skill performs broader data handling and persistent secret storage than advertised.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.