ClawHub
Back to skill

Security audit

PixVerse 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 disclosed AI Hive video-generation helper that uploads only user-specified media and uses an AI Hive API key for its stated purpose.

Install only if you intend to use AI Hive for video generation and are comfortable sending prompts and explicitly selected media files to AI Hive/object storage. Review the API key storage location (~/.ai-hive/config.json), keep that file private, and use --no-download or --output-dir if you want to control where generated results are saved.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
描述将技能定位为把 PixVerse 类短片“迁移为可审的动作与转场方案”，听起来更像分析/规划/替代工作流说明；但代码的核心行为是直接调用 AI Hive OpenAPI 进行视频生成、编辑、延长，并下载最终视频结果。这是用途上的实质差异。此外，代码还包含独立上传素材、查询任务状态、轮询下载结果、以及浏览器引导创建 API Key 等能力，这些都未在描述中体现。虽然描述提到支持文生、图片起动、参考节奏、视频编辑和片尾延长，与部分生成模式相符，但对技能主要功能的表述明显弱化或偏离了实际“视频生成工具/API 客户端”的性质，因此应判定为不匹配。

Vague Triggers

Medium
Confidence
92% confidence
Finding
The description says to use the skill when users search for broad terms like “特效视频”, “社媒短片”, and “视频生成编辑”, which are generic requests rather than narrowly scoped triggers. Although the file states this is a PixVerse alternative, the trigger list lacks clear constraints or negative examples to distinguish when this skill should not activate.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The module docstring and all user-facing CLI guidance are written exclusively in Chinese, and the script later hardcodes Chinese prompts/messages for initialization and operation. This creates a language/locale policy issue because the skill does not offer users an opt-in choice of language or explain that it is intentionally restricted to a Chinese-speaking or region-specific audience.

Env Variable Harvesting

High
Category
Data Exfiltration
Content
def _resolve_api_key(self, cli_key):
        if cli_key:
            return cli_key
        env_key = os.environ.get("AI_HIVE_API_KEY")
        if env_key:
            return env_key
        file_config = self._read_config_file()
Confidence
70% confidence
Finding
Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.

Env Variable Harvesting

High
Category
Data Exfiltration
Content
def _try_read_existing_api_key():
    """安全读取已配置的 API Key，失败返回 None。"""
    env_key = os.environ.get("AI_HIVE_API_KEY")
    if env_key:
        return env_key
    try:
Confidence
70% confidence
Finding
Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.