ClawHub
Back to skill

Security audit

1688 电商图片生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill is a purpose-aligned AI Hive image-generation helper for 1688 product imagery, with expected API-key setup, user-selected uploads, and local output downloads.

Install only if you are comfortable using AI Hive, storing an API key locally, uploading selected product/reference images to that service, and saving generated results under the default output directory or one you choose. Review the script if you want assurance that the dormant generic helper functions remain unexposed.

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
92% confidence
Finding
The skill invokes shell commands, installs packages, accesses files, reads environment-derived paths, and performs network operations, yet it declares no permissions. This creates a transparency and governance gap: users and enforcement layers cannot accurately assess or constrain what the skill can do, increasing the chance of unintended data access, command execution, or outbound requests.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The skill is presented as a narrowly scoped 1688 ecommerce image tool, but the underlying behavior reportedly includes broad AI Hive capabilities such as text chat, video generation, media upload, wallet/user queries, model enumeration, and interactive API-key setup. This mismatch is dangerous because users may grant trust and provide sensitive business assets under a limited-purpose expectation while the skill can perform much broader actions and potentially exfiltrate data or expand usage beyond its stated scope.

Static analysis

No suspicious patterns detected.