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 clearly routes user-requested TikTok research tasks through Gecho’s MCP tools, with disclosed browser-session use and local result saving.

Before installing, be aware that Gecho works through your logged-in Chrome/TikTok session and may save collected TikTok metadata, comments, URLs, and insight results to local JSON files. Use a dedicated save directory when possible and review/delete saved outputs if the machine is shared.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill states that raw results will be saved locally and paths may be returned, but it does not clearly warn users before persistence occurs or explain retention/privacy implications. Since collected TikTok metadata, comments, and URLs may contain sensitive or regulated content, silent local writes increase the risk of unintended data storage, disclosure, or policy violations on shared systems.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger guidance is broad enough that an agent may invoke this skill for generic TikTok-related discussion, not just when the user explicitly wants data collection or Gecho tooling. Because this skill can initiate browser-mediated scraping workflows and local file output, accidental activation can cause unnecessary data access, unintended network actions, or confusing tool use beyond user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

文件从描述到示例、模板和输出规范均固定为中文，且未说明这是可选语言或仅适用于特定中文用户群。根据语言/区域政策，若技能默认限制某一语言而不给用户选择，可能构成自然语言层面的语言策略问题。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.