ClawHub
Back to skill

Security audit

社媒营销视频生成与编辑

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AI Hive video-generation helper that uploads user-chosen marketing media and downloads generated outputs.

Install only if you are comfortable sending the chosen marketing videos/images and prompts to AI Hive, and use --preview first for costly jobs. Store the API key only on machines you trust, or pass it per command instead of saving it.

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
95% confidence
Finding
The skill instructs the agent to run local Python scripts, read local media files, use environment/config-based API keys, make network requests to AI Hive, and write/download outputs, but it declares no permissions. That mismatch is dangerous because users and policy layers cannot accurately understand or constrain what the skill will access or transmit, increasing the risk of unintended file access, secret exposure, and external data exfiltration.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.