ClawHub
Back to skill

Security audit

爆款视频故事结构原创复刻｜AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-HIVE video workflow helper that uses user-provided media, an API key, network calls, and ffmpeg in ways that fit its stated purpose.

Install only if you are comfortable providing an AI-HIVE API key, uploading selected reference media to AI-HIVE/object storage, and potentially incurring generation costs. Use only authorized media, review prompts and routing before running generation, and avoid storing or sharing real API keys in logs or project files.

SkillSpector

Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill advertises executable workflows that use environment variables, local file access, network requests, and shell-invoked tooling such as ffmpeg, but no permissions are explicitly declared. That creates a trust and review gap: consumers may invoke the skill without understanding that it can access local paths, external services, and potentially billable operations.

Tp4

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding
The documented purpose is narrowly framed as story-structure remake assistance, but the embedded behavior includes broader chat, image generation, media upload, and ffmpeg-based media manipulation. This mismatch is dangerous because it can hide materially broader capabilities than users and reviewers expect, including arbitrary content generation, data exfiltration through uploads, and local media processing with security and cost implications.

Static analysis

No suspicious patterns detected.