ClawHub
Back to skill

Security audit

Seedream 5.0 Lite 电商主图

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AI image-generation helper that uses an API key, uploads user-selected images, and saves generated outputs, with some non-enforcing review guidance users should understand.

Install only if you are comfortable giving AI Hive an API key and uploading the product/reference images you choose. Treat platform-rule, SKU, and promotional-compliance checks as your own review responsibility, not as automatic guarantees from the script.

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
91% confidence
Finding
The skill advertises operational capabilities that include shell execution, filesystem access, environment access, and network use, yet declares no permissions. This creates a transparency and trust problem: users and reviewers cannot accurately assess the skill’s actual access level, and those capabilities are sufficient to read local data, write persistent files, and make outbound requests if the backing script is invoked.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The documented behavior materially understates what the skill can do: it can obtain and persist an API key, upload local images, query arbitrary task IDs, download files locally, and pass arbitrary model parameters, while claiming safety gates that are not actually implemented. This is dangerous because users may trust compliance and review guarantees that do not exist, and the undeclared data flows can expose secrets, local files, generated assets, or other users’ task metadata.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.