ClawHub
Back to skill

Security audit

商品图片套图生成与编辑｜Product Image Suite

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed product-image generation helper that uploads user-chosen reference images to a fixed AI Hive API and saves generated outputs locally.

Install only if you are comfortable sending the reference product images you choose to AI Hive, and use the brief command when you want to inspect prompts without uploading images or creating generation tasks.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs users to run Python and shell commands that perform network access, file reads/writes, and likely use environment-derived values such as SKILL_PATH, yet it declares no permissions. This creates a transparency and governance gap: operators may execute a skill with broader capabilities than expected, increasing the risk of unreviewed data handling, outbound uploads of local images, and shell-based misuse in environments that rely on declared permissions for enforcement.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.