ClawHub
Back to skill

Security audit

Veo 视频生成替代｜AI 视频生成与编辑

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent AI video-generation helper that uses a disclosed AI Hive service, with some credential and media-upload handling users should understand before use.

Install/use this only if you are comfortable sending prompts and any selected image or video files to AI Hive. Use --api-key or AI_HIVE_API_KEY if you do not want the setup command to store a key locally, and delete ~/.ai-hive/config.json to remove a saved key.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill exposes significant execution capabilities by instructing use of Python scripts that read local files, write data, access environment variables, invoke shell commands, and make outbound network requests, yet it declares no permissions. This mismatch undermines user and platform trust boundaries because the skill can process local media and transmit API credentials or content to a remote service without an explicit permission model.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The manifest uses very broad trigger phrases such as general video-editing, advertising, and product-video requests, which can cause the skill to activate for many common creative tasks beyond a narrow Veo-migration use case. Overbroad routing increases the chance that users are steered into executing a networked, file-processing skill unexpectedly, raising consent and data-handling risks.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The setup command persists the API key to ~/.ai-hive/config.json on disk. Although the file mode is set to 0600, the tool does not clearly warn the user that credentials will be stored locally, which creates avoidable exposure on shared systems, backups, or endpoint compromise.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The attach function uploads local image/video files to a remote AI Hive service after obtaining an upload token, but the user-facing flow does not prominently disclose that selected media will be transmitted off-device. This can lead to unintended exfiltration of sensitive or proprietary media, especially because the skill handles arbitrary local files provided by the user.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.