ClawHub
Back to skill

Security audit

TikTok 全链路调研：爆款视频搜索、达人采集、单条视频详情、选品、趋势、竞品与内容洞察【Gecho 官方】

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed TikTok research integration that uses Gecho's MCP and Chrome extension to collect and summarize TikTok search, video, comment, creator, and insight data, with privacy considerations users should understand before use.

Install only if you are comfortable connecting Gecho to a logged-in TikTok browser session and storing collected TikTok metadata, comments, replies, and insight outputs locally. Review the Gecho MCP package and Chrome extension, choose an appropriate save directory, and delete exported JSON files when you no longer need them.

SkillSpector

Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Intent-Code Divergence

Medium
Confidence
89% confidence
Finding
The skill requires a logged-in TikTok browser session and explicitly collects comments, replies, creator videos, and insight outputs from that session, yet the FAQ reassures users that private account information is not collected. That claim is overly broad and potentially misleading because session-accessible data can include sensitive or account-scoped content, causing users to consent without understanding the real privacy exposure.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs the tool to save harvested TikTok data to local JSON files but does not prominently warn users about the privacy and data-handling implications of storing potentially sensitive metadata, comments, replies, and research outputs on disk. This can lead to unintentional retention, broader local exposure, or later disclosure through backups, shared workspaces, or weak filesystem permissions.

Static analysis

No suspicious patterns detected.