ClawHub
Back to skill

Security audit

AI UGC广告生成器｜AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed AI-HIVE ad-generation workflow that uses user-provided media, an API key, external generation APIs, and local video tools in ways that fit its stated purpose.

Install only if you intend to use AI-HIVE for UGC/ecommerce ad generation. Expect it to store an API key if you run init, upload only files you explicitly provide as references, make billable API calls only after you confirm parameters, and use ffmpeg for local video edits. Do not use it with unauthorized media, sensitive private footage, or unsupported product claims.

SkillSpector

Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill advertises and demonstrates code paths that can access environment variables, the filesystem, the network, and the shell, yet it does not declare permissions or narrowly scope those capabilities. That creates a trust-boundary problem: a caller may invoke a seemingly content-generation skill without realizing it can read local files, persist data, make outbound requests, or execute local tooling such as ffmpeg.

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding
The documented purpose is a specialized UGC ad generator, but the behavior includes broader capabilities such as generic AI-HIVE chat, model/user-info lookup, media upload tooling, local credential handling, browser opening, and standalone ffmpeg manipulation. This mismatch is dangerous because users and reviewers may grant trust or run the skill under false assumptions, while the extra behaviors expand attack surface for data exfiltration, unintended billing, and local side effects.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The default prompt is broad enough to activate the skill for loosely related requests and immediately steer execution into a 'production-ready' workflow with runnable AI-HIVE commands. In a skill that can generate ad scripts, upload reference materials, query pricing, and trigger external API workflows, ambiguous invocation increases the chance of unintended use, policy bypass through over-application, or accidental processing of sensitive/commercial inputs.

Static analysis

No suspicious patterns detected.