ClawHub
Back to skill

Security audit

tiktok-scraper

Security checks for vulnerabilities and agentic risk

Overview

This is a documented TikTok API helper with no bundled executable code, though users should know it sends lookups to CreatorCrawl and can retrieve social-media data.

Install this only if you want Codex to use CreatorCrawl for live TikTok lookups. Treat queries, TikTok URLs, handles, and requested lookup parameters as data sent to CreatorCrawl, and use the skill deliberately for TikTok-specific research, especially when retrieving comments, transcripts, followers, or following lists.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
97% confidence
Finding

The invocation description is broad enough to trigger on generic requests about creators, videos, trends, or social media research, which can cause the agent to call an external API more often than users would reasonably expect. In this skill's context, over-invocation increases the chance of unnecessary disclosure of user queries to a third-party service and unnecessary collection of TikTok-related data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill advertises access to comments, follower/following data, and transcripts from a live external API without warning users that their request content may be sent to a third party and that returned data may include sensitive or privacy-impacting information. In this context, the skill is specifically designed to retrieve potentially sensitive social-media data, so missing user-facing notice meaningfully raises privacy and consent risks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.