ClawHub
Back to skill

Security audit

analyzing-competitor-tiktok-content-strategy

Security checks across malware telemetry and agentic risk

Overview

The skill mostly does what it claims, but it exposes an overbroad custom JavaScript option and broad scraping inputs that users should review before installing.

Review this skill before installing if you do not want agents to run broad TikTok scraping or pass custom JavaScript to Apify actors. Use tight maxItems limits, avoid customMapFunction unless you fully trust the code, and treat APIFY_TOKEN plus scraped outputs as sensitive because requests and results may go through Apify and may be saved locally.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Context-Inappropriate Capability

High
Confidence
94% confidence
Finding
Exposing a `customMapFunction` parameter that accepts arbitrary JavaScript introduces a code-injection/code-execution pathway through an otherwise analysis-focused skill. Even if execution occurs inside a third-party actor environment, it expands the skill from data retrieval into user-supplied code execution, which can be abused for unauthorized processing, exfiltration, or unexpected resource use.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill sends account identifiers and scraping requests to Apify and also documents saving results to local files, but it does not clearly warn users about this third-party transmission and persistence behavior. That omission can cause unintentional disclosure of research targets, query terms, or collected datasets to external services or local storage.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The manifest describes a skill focused on analyzing a competitor's TikTok content strategy from competitor profiles and top-performing videos. However, the documented inputs allow hashtags, music pages, search, locations, keyword-based discovery, regional filtering, and custom output transformation, which substantially broadens behavior beyond competitor account analysis into general TikTok search and scraping.

External Transmission

Medium
Category
Data Exfiltration
Content
**REST API fallback:**
```bash
curl -X POST \
  "https://api.apify.com/v2/acts/apidojo~tiktok-profile-scraper/runs?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"usernames": ["[handle1]", "[handle2]"]}'
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
**REST API fallback:**
```bash
curl -X POST \
  "https://api.apify.com/v2/acts/apidojo~tiktok-profile-scraper/runs?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"usernames": ["[handle1]", "[handle2]"]}'
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
**REST API fallback:**
```bash
curl -X POST \
  "https://api.apify.com/v2/acts/apidojo~tiktok-profile-scraper/runs?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"usernames": ["[handle1]", "[handle2]"]}'
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

VirusTotal

49/49 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.