ClawHub
Back to skill

Security audit

Seedance 2.5 产品宣传视频

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed product-video generation helper that uses user-provided media and an AI Hive API key to create and download video shots.

Before installing, be aware that using non-preview generation uploads the product images and any motion-reference video you provide to AI Hive or its HTTPS upload destination, and it uses your AI Hive API key for billable generation. Use --preview first for prompt review, keep the API key private, and only pass media you are allowed to upload.

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
92% confidence
Finding
The skill instructs users to run a local Python script, install dependencies, use API keys from environment/config files, read local media files, and make outbound network requests, yet it declares no permissions. This creates a transparency and consent gap: users may execute a skill with access to files, secrets, shell, and network without explicit permission disclosure, increasing the risk of unintended data exposure or misuse if the script or its dependencies are modified or abused.

VirusTotal

42/42 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.