ClawHub
Back to skill

Security audit

高转化广告图片生成与编辑

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent AI Hive ad-image generation helper, with expected API-key use and user-directed image upload, though users should understand that prompts and images go to AI Hive.

Install only if you are comfortable using AI Hive for this workflow. Treat prompts, product images, brand assets, and generated-task data as leaving your machine for cloud processing, and avoid submitting confidential or unauthorized ad assets. Use the init command only when you intend to store an AI Hive API key locally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (8)

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
存在明显不匹配。描述强调的是一套面向广告转化优化的方法论与分析能力，不仅生成/编辑图片，还应包含漏斗诊断、信息匹配、单变量实验和基于真实结果的复盘；但代码仅实现了调用 AI Hive 官方 API 的图片生成与编辑相关基础操作，以及配套的上传、轮询、下载和 API Key 初始化。也就是说，代码缺少描述中的核心分析/优化能力，同时还包含描述未提到的浏览器打开、API Key 配置、任务查询和文件下载等功能。虽然这些额外功能多为工具性支持，但描述对能力范围的表述明显超过了代码实际行为，因此应判定为不匹配。

Context-Inappropriate Capability

Low
Confidence
81% confidence
Finding
The manifest describes a skill for generating and editing high-conversion ad images via AI Hive, but this code also opens a local web browser and appends attribution parameters (`from=cli-skill&skill=...`) to an onboarding URL. While credential setup is tangentially useful, launching a browser for interactive account flow is not a direct or obvious requirement of the stated image-generation purpose.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The manifest description says to use the skill for broad phrases like '高转化广告图片生成与编辑' and 'performance creative' without narrowing context, trigger boundaries, or exclusion conditions. These phrases are generic enough to match many ordinary marketing or image-editing requests, which could cause unintended invocation.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill description states that keyed requests are sent to 'https://ai-hive.iclip.cn/api', but it does not explicitly disclose that user-supplied images and prompt content may be transmitted off-system to that external service. Because the skill processes ad assets and possibly branded or sensitive images, a clear privacy/data-transfer warning is expected in the markdown description.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The module docstring and all user-facing CLI prompts/messages are written only in Chinese, which imposes a specific language on users. The file does not offer an opt-in language selection or explain that the skill 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
os.environ.get("AI_HIVE_API_KEY

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
os.environ.get("AI_HIVE_API_KEY

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.