ClawHub
Back to skill

Security audit

tiktok-video-search

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed TikTok search integration that uses Gecho's browser-session workflow and local result files in ways that match its stated purpose.

Install only if you are comfortable using Gecho Bridge and its Chrome extension with a logged-in TikTok session. Treat saved search-result JSON files as potentially sensitive research records, especially on shared machines, and choose or clean the save directory accordingly.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill explicitly states that it saves the full raw TikTok result set to a local JSON file, but the main user-facing flow does not clearly warn users that search results and associated metadata will persist on disk. This creates privacy and data-handling risk, especially if results contain creator identifiers, links, engagement data, or potentially sensitive research terms and are stored in shared or insecure directories.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill requires the user to be logged in to TikTok and to use a browser extension that bridges data from the live browser session, but it does not present a prominent upfront privacy warning about access to session-derived platform data. That omission can mislead users about the sensitivity of the setup and increases the risk of unintentional exposure of browsing-session data or account-linked content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.