Security audit

guaikei-douyin-intel-exchange

Security checks across malware telemetry and agentic risk

Overview

The skill is purpose-aligned, but it should be reviewed because it sends Douyin queries and tokens to a third-party service and automatically stores large social-data exports locally.

Install only if you are comfortable sending Douyin search terms, video/account URLs, and the GUAIKEI token to the Guaikei service, and treat generated logs as potentially sensitive because they may contain public user identifiers, comments, and business research topics. Delete logs when no longer needed and avoid using the skill for generic research unless Douyin collection is explicitly intended.

SkillSpector

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 (7)

Description-Behavior Mismatch

Medium

Confidence: 91% confidence
Finding: The CLI writes fetched comment data to a local JSON file automatically after successful execution. Because comment content may contain personal data, identifiers, or sensitive business intelligence, silent persistence increases the risk of unintended retention, later disclosure, or collection beyond user expectations.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The description says the skill should be used even when the user does not mention Douyin, which broadens activation beyond clear user intent. That can cause unintended data access or execution in contexts where the user asked for generic research, increasing the chance of over-collection, wrong-tool invocation, and privacy/compliance mistakes.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The README explicitly promotes exporting large volumes of scraped Douyin data, including comments and author information, to local JSON logs but does not warn that these datasets may contain personal data or sensitive content. This increases the risk of unintended retention, mishandling, or secondary sharing of scraped personal information, especially in marketing or monitoring workflows.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The README instructs users to obtain and configure a GUAIKEI_API_TOKEN from an external website, which implies that user queries and target Douyin data are sent to a third-party service, but it does not clearly disclose this data flow. Users may assume the tool operates locally because it is described as 'Node.js 一键运行' and '无需部署服务', creating a transparency and consent gap around external transmission of search terms, URLs, and retrieved content.

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The code sends both the search keyword and the skill token as URL query parameters in the GET request. Query parameters are more likely to be logged by servers, proxies, browser/network tooling, and observability systems, which can expose sensitive tokens and user search terms beyond their intended recipients.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The tool stores comment results locally without any explicit user-facing disclosure in this file, creating a transparency and privacy problem. Users may believe the tool only prints results to stdout, while it also creates a durable local record that could be accessed by other users, processes, backups, or later workflows.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The CLI persists the full search output and user-supplied keyword to a local JSON file without explicit consent, redaction, or any visible retention control. In this skill’s context, queries may reveal research topics, competitor analysis, campaign plans, or sensitive business intent, and the results may include third-party content metadata that becomes exposed to other local users, backups, or log collectors.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.