ClawHub
Back to skill

Security audit

Wan2.5 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-selected media, stores an API key locally, submits generation jobs, and downloads results.

Before installing, understand that media files you choose may be uploaded to AI Hive, generation may incur API costs, and the init command stores your API key locally. Use --no-download for submit-only runs and review costs before bulk jobs.

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
95% confidence
Finding
The skill documentation describes capabilities that read environment variables, write local configuration files, access the network, and invoke shell commands, yet no permissions are declared. This creates a transparency and consent gap: users and hosting platforms may not realize the skill can access sensitive local state and make external requests, which increases the risk of unintended secret exposure or filesystem modification.

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding
The skill claims a narrow purpose around Wan2.5 video generation/editing, but the described/runtime behavior also includes broader capabilities such as listing all models, retrieving account or wallet information, opening a browser, and persisting API keys locally. This mismatch undermines informed consent and could expose sensitive account data or trigger actions the user did not expect from a media-generation workflow.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.