ClawHub
Back to skill

Security audit

AI开箱视频生成器｜AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-HIVE unboxing-video workflow with expected API, upload, download, and local video-editing helpers, but users should be careful with paid generation and API-key storage.

Install only if you intend to use AI-HIVE for product or marketing video generation. Review prompts and routing before submitting paid jobs, upload only media you are authorized to use, and protect or remove the stored API key if you no longer need the tool.

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
93% confidence
Finding
The skill documents executable capabilities including environment-variable access, file read/write, shell usage, and network access, yet it declares no permissions. That gap weakens review and consent boundaries because a host system or user may underestimate what the skill can do, especially since it also includes commands that process local files and call external APIs. In this context, the issue is more dangerous because the skill is designed to handle uploads, downloads, and local media operations, so undeclared capabilities materially expand the attack surface.

Tp4

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding
The skill is presented as a narrowly scoped AI unboxing-video tool, but the documented behavior extends into generic chat, generic image generation, account/model querying, standalone uploads, API-key initialization, and broad local ffmpeg operations. Scope drift like this is dangerous because users and reviewers may authorize a specialized marketing workflow while actually exposing credentials, local media, and broader external API functionality than expected. The mismatch increases risk in this context because the skill already combines network access, local file handling, and shell-capable media tooling.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill enables implicit invocation without any visible activation constraints, so the agent may auto-select this capability in situations where the user did not clearly request AI-HIVE video generation. Because this skill is designed to produce runnable commands and workflow steps for external API usage, over-broad auto-invocation increases the chance of unintended tool use, unwanted external requests, or generation of policy-sensitive marketing content without explicit user confirmation.

Static analysis

No suspicious patterns detected.