ClawHub
Back to skill

Security audit

抖音爆款短视频拆解｜AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-HIVE video workflow helper; it uses local files, an API key, uploads, and downloads in ways that fit its stated purpose.

Install only if you are comfortable giving AI-HIVE an API key and uploading the specific media files you choose for generation. Use authorized assets, avoid pasting real API keys into chats or logs, and review parameters before running any paid generation command.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill exposes operational capabilities including environment access, filesystem access, network calls, and shell execution, but does not declare permissions or clearly bound how those capabilities are controlled. That creates a trust and review gap: users and hosting systems cannot accurately assess what the skill may do with local files, secrets, or external services before execution.

Tp4

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding
The documented purpose is narrow video-decomposition and optional AI-HIVE generation, but the referenced behavior includes broader generic chat/image generation, browser-based API key initialization with local config storage, and extensive ffmpeg editing operations. This mismatch can mislead users and reviewers about the real attack surface, increasing the chance of secret exposure, unintended file processing, or execution of capabilities the user did not knowingly authorize.

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The file is implemented as a broad, generic AI-Hive CLI for chat, image, video, model listing, uploads, and task polling, while the manifest describes a much narrower Douyin video decomposition/generation skill. This scope mismatch increases attack surface and allows use of capabilities the user may not expect, including arbitrary text/image/video generation and model discovery outside the declared workflow.

Description-Behavior Mismatch

Low
Confidence
78% confidence
Finding
The skill exposes a user-info endpoint that retrieves account information and wallet balance even though that access is not described in the stated workflow. Undisclosed account-data access is risky because operators may invoke it without user expectation or need, expanding sensitive data exposure beyond the skill's purpose.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The upload flow sends local media files to remote object storage and the AI-Hive service without an explicit privacy or transmission warning at the point of action. In this skill context, users may upload commercial creatives, reference videos, or potentially sensitive media; undisclosed remote transfer can lead to unintended disclosure of proprietary or personal content.

Static analysis

No suspicious patterns detected.