ClawHub
Back to skill

Security audit

Instagram INS 电商视频生成与编辑

Security checks across malware telemetry and agentic risk

Overview

This skill is an API-backed Instagram video generation helper with expected credential setup, media upload, task polling, and output download behavior.

Before installing, understand that this skill sends prompts and any media paths you provide to AI Hive, stores an API key locally if you run init, and downloads generated files to ~/Downloads/AiHive by default. Use it only with media you have rights to upload and an AI Hive account/API key you intend to use for this workflow.

SkillSpector

By NVIDIA
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
84% confidence
Finding
The skill advertises only content-creation behavior in SKILL.md, but the documented runtime invokes a Python script that appears to require broad capabilities including shell, network, environment access, and file read/write, without any declared permissions or clear scoping. This creates unnecessary trust ambiguity: an operator may run the skill assuming limited behavior, while the underlying implementation can access local files, environment secrets, and external services.

Tp4

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding
The skill description promises an Instagram e-commerce video workflow, but the associated behavior reportedly includes generic chat/image generation, model discovery, wallet and user-info retrieval, media upload utilities, and API-key/browser setup flows unrelated to the declared purpose. This mismatch is dangerous because it can mask broader data access and external actions, preventing users and reviewers from making informed trust decisions and increasing the chance of unintended credential exposure or unauthorized API operations.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.