ClawHub
Back to skill

Security audit

guaikei-douyin-author-posts-to-feed-export

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Douyin public-data retrieval tool that uses a third-party API token and saves result JSON files locally, with no evidence of hidden destructive or exfiltrating behavior.

Before installing, confirm you are comfortable using the third-party Guaikei API token, sending Douyin keywords or URLs to that service, and retaining exported public data in local logs. Protect GUAIKEI_API_TOKEN and periodically delete logs containing comments or account data if you no longer need them.

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Description-Behavior Mismatch

Low
Confidence
91% confidence
Finding
The CLI writes fetched comment data to a local JSON log file after completing what is presented as a read-oriented retrieval operation. This creates an unexpected persistence side effect: comments may contain personal data, sensitive content, or regulated information, and storing them locally increases the risk of unauthorized access, retention beyond user intent, or accidental disclosure.

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The CLI persists the full exported post results to a local JSON file after completing the user-requested retrieval. This creates an additional data-retention side effect not implied by the skill description, increasing the risk of unintended disclosure of scraped/exported content, filesystem accumulation, and later access by other local users or processes.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The CLI writes full search results to a local log file named with user-supplied query content, even though the advertised behavior is just retrieval/display. This creates an unnecessary data-retention channel on disk that can expose user queries and fetched content to other local users, backup systems, or later unintended processing.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.