Back to skill

Security audit

Douyin Keyword Collector

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Douyin keyword-suggestion browser automation guide, with the main caution being account privacy if the user chooses to log in.

Use this skill logged out when possible. If Douyin requires login, use a separate low-privilege account because the browser automation may see account-personalized page content while collecting suggestions.

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
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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly recommends that the user manually scan a QR code to log in if search suggestions are unavailable, but it does not clearly warn that subsequent browser automation may operate in an authenticated Douyin session and expose account-associated browsing context, cookies, or personalized data to the automation flow. This creates a meaningful privacy and account-safety risk, especially because the skill is designed to interact with a live consumer website rather than an isolated API.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.