ClawHub
Back to skill

Security audit

"dataify-tiktok-comment-by-url"

Security checks across malware telemetry and agentic risk

Overview

This skill coherently builds Dataify TikTok scraper curl requests, but users should handle the API token carefully.

Install only if you intend to use Dataify for TikTok scraping. Treat DATAIFY_API_TOKEN like a password: prefer a session-scoped or secret-manager setup when possible, avoid exposing it in shared shell profile files, and review the generated curl command before running it because it will send your selected URLs/parameters to Dataify.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill uses environment-variable access, local file reads, and shell command generation but does not declare those capabilities. Hidden capability use weakens reviewability and can surprise hosts or users about what the skill can access, especially because it handles an API token and reads local reference files. In this context, the issue is more dangerous because the workflow explicitly touches credentials and constructs commands for external transmission.

Description-Behavior Mismatch

Medium
Confidence
88% confidence
Finding
The manifest says the skill is rooted at tiktok_comment_by-url, but the workflow offers multiple different TikTok tools, creating a scope mismatch. This can mislead operators and reviewers about what the skill actually does and may cause users to invoke unintended scrapers or send data to the wrong spider_id. The mismatch increases risk because downstream requests are authenticated with a bearer token.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs users to persist DATAIFY_API_TOKEN in shell profile files and even source them, but it does not warn about credential sensitivity, file permissions, shell history exposure, or shared-account risks. Persisting bearer tokens in broadly readable startup files can lead to credential theft and unauthorized use of the Dataify account. This is more dangerous here because the token is later used for authenticated outbound requests.

External Transmission

Medium
Category
Data Exfiltration
Content
---
name: "dataify-tiktok-comment-by-url"
description: "Prepare Dataify builder requests for the tiktok.com scraper family rooted at tiktok_comment_by-url. Use  when needs to work with the successful Dataify scraper detail entry for tiktok_comment_by-url, let the user choose one of its available tools, read saved getToolParams options, and generate a scraperapi.dataify.com/builder curl request with DATAIFY_API_TOKEN."
---

# Dataify Builder Skill
Confidence
90% confidence
Finding
curl request with DATAIFY_API_TOKEN." --- # Dataify Builder Skill Use this skill to prepare Dataify builder requests for the scraper family rooted at `tiktok_comment_by-url` on `tiktok.com`. ## Wor

External Transmission

Medium
Category
Data Exfiltration
Content
---
name: "dataify-tiktok-comment-by-url"
description: "为 tiktok.com 上以 tiktok_comment_by-url 为根的 scraper 系列准备 Dataify builder 请求。当需要处理成功的 Dataify scraper detail 条目 tiktok_comment_by-url、让用户选择可用工具、读取已保存的 getToolParams 选项，并使用 DATAIFY_API_TOKEN 生成 scraperapi.dataify.com/builder curl 请求时，使用此 skill。"
---

# Dataify Builder Skill 中文版
Confidence
87% confidence
Finding
curl 请求时，使用此 skill。" --- # Dataify Builder Skill 中文版 这个 skill 用于为 `tiktok.com` 下、以 `tiktok_comment_by-url` 为入口的 Dataify scraper 工具族生成 builder 请求。 ## 工作流程 1. 先检查环境变量中是否存在 `DATAIFY_API_TOKEN`。 2. 如果

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.