Security audit

guaikei-douyin-comment-threads

Security checks across malware telemetry and agentic risk

Overview

This is a read-only Douyin public-data tool with disclosed third-party API use and local JSON logging, so the main risks are privacy and log handling rather than malicious behavior.

Install only if you are comfortable sending Douyin research inputs and the GUAIKEI_API_TOKEN to guaikei.com and keeping fetched public data in local JSON log files. Avoid confidential targets or regulated data, protect the token, and delete or secure the logs directory when results should not persist.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Description-Behavior Mismatch

Medium

Confidence: 94% confidence
Finding: The CLI persists the fetched Douyin results to a local JSON file after completing what is presented as a read-oriented analysis workflow. This creates an undisclosed data-at-rest side effect: scraped account data and metadata may remain on disk, exposing user activity, third-party content, or operational intelligence to other local users, backups, or later compromise.

Vague Triggers

High

Confidence: 94% confidence
Finding: The trigger text explicitly says the skill should be used even when the user does not mention Douyin, which makes invocation overly broad and increases the chance that unrelated requests are routed to a third-party data service. That can cause unintended external transmission of user queries or URLs and lead to privacy, consent, and data-minimization failures.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The examples and usage guidance encourage API calls with keywords, video URLs, and account links, but there is no prominent warning near those examples that this data will be sent to guaikei.com's third-party service. Users may unknowingly disclose sensitive research targets, competitor lists, or internal investigation topics to an external provider.

Missing User Warnings

Low

Confidence: 90% confidence
Finding: The README states that JSON logs are automatically written to a local logs directory, but it does not clearly warn that collected Douyin search, post, and comment data may contain sensitive or regulated information and will persist on disk. This can lead to unintentional retention, sharing, or exposure of scraped data on multi-user systems or in synced folders.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The tool writes full fetched results to a predictable local JSON file without warning, confirmation, or user consent. In this skill context, operators may use it to inspect competitors, comment feedback, and trends, so silent retention increases the risk of leaking sensitive business research, collected content, and usage metadata through shared hosts, endpoint monitoring, or accidental disclosure.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The CLI persists full search output, including queried keywords and returned results, to a local JSON file by default without explicit user consent or a clear warning. In this skill's context—competitive research, account analysis, comments, and trend monitoring—that data can contain sensitive business intelligence or potentially personal data, so silent persistence increases the risk of unintended disclosure through shared machines, backups, or later exfiltration.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.