ClawHub
Back to skill

Security audit

Douyin & TikTok Trend Fetcher

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides the agent to fetch public TikTok Creative Center trend pages and summarize them.

Installers should understand that results come from TikTok Creative Center's English/global pages by default and may not match a specific country, language, or China-specific Douyin market unless the user asks the agent to qualify those limits.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill description includes broad natural-language trigger phrases like 'what's trending on TikTok/Douyin right now' and 'content trends,' which can cause the skill to activate for loosely related user requests. Unintended invocation can lead to unnecessary external fetches, user confusion, and data being pulled from third-party sites when the user did not specifically request this skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill hard-codes /pc/en Creative Center URLs, forcing English-language/global views without checking the user's locale or preferences. This can produce misleading or inappropriate results for users expecting region-specific or language-appropriate trend data, especially because trend rankings are highly locale-dependent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.