guaikei-douyin-json-comments-export

• Outcome: Review
• Latest audit: Aug 20, 2026 · 2:55 AM UTC
• Version: 1.0.0

Overview

The skill largely matches its Douyin public-data export purpose, but it has broad auto-trigger wording, sends token-backed requests to a third-party API, and saves fetched data locally by default.

Install only if you are comfortable sending Douyin URLs, search keywords, request limits, and your GUAIKEI_API_TOKEN to guaikei.com, and with retrieved results being saved in the skill's logs directory by default. Use explicit Douyin-related prompts, protect the token, and delete or restrict logs if they contain comments, account data, or sensitive research terms.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (10)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill declares use of an environment variable token and command execution behavior but does not declare corresponding permissions, creating a mismatch between documented capabilities and the permission model. This can undermine least-privilege controls and make secret access less visible to reviewers or runtime policy enforcement.

Description-Behavior Mismatch

Medium

• Confidence: 91% confidence
• Finding: The CLI persists fetched comment data to a local JSON file after completing the requested retrieval, which expands data handling beyond transient display. Even though the data is described as public, comments can still contain personal information or sensitive content, and undocumented retention increases privacy, compliance, and data-leak risk on shared systems.

Vague Triggers

Medium

• Confidence: 83% confidence
• Finding: The implicit trigger phrases are broad enough to capture generic research or competitive-analysis requests that may not be clearly about Douyin, increasing the chance the skill runs unexpectedly. Over-broad auto-invocation can cause unintended data access, external requests, or collection of platform data when the user did not explicitly request this tool.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The natural-language trigger examples are broad enough that normal user phrasing like '找一下' or references to '视频' could activate scraping actions without the user clearly intending to run this skill. In an agent setting, this can cause unintended collection of third-party platform data and execution of external commands based on ambiguous requests.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The intent-recognition priority rules rely on generic keywords such as '搜索', '找', '热点', and '榜单' without enough domain constraints, which increases the chance of accidental activation from everyday conversation. Because this skill performs data extraction and logging, misrouting ambiguous user input can lead to unauthorized or unexpected scraping and local persistence of collected data.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The README promotes automatic export of comments and scraped public data to JSON logs, but it does not clearly warn that comments may contain personal or sensitive information and that these records will be stored locally. This creates a privacy and data-handling risk, especially in shared environments or when users may not realize retention and redistribution implications.

Missing User Warnings

Medium

• Confidence: 80% confidence
• Finding: The GET request places the token in query parameters, which are commonly recorded in server logs, proxies, browser history, monitoring systems, and error traces. If the token is a bearer-style credential, exposure through URLs can enable unauthorized API access and data retrieval.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: The tool sends the supplied URL and requested limits to a remote API to create and fetch a comment task, but there is no explicit notice or consent flow that user input and retrieved data will be transmitted to an external service and later persisted locally. This is risky because users may assume a local-only analysis workflow based on the skill framing, leading to unanticipated disclosure and retention of data.

Missing User Warnings

Medium

• Confidence: 85% confidence
• Finding: The CLI automatically persists retrieved Douyin post data to a local JSON file after successful execution, without explicit user notice, consent, or any control to disable persistence. In a data-collection skill, this creates unintended at-rest storage of potentially sensitive or regulated scraped data, increasing exposure through local compromise, accidental sharing, backups, or multi-user environments.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The CLI writes the full search output to a local JSON file automatically, using a filename derived from user input, without an explicit opt-in or warning. In a data-export skill, this can unintentionally persist potentially sensitive research terms and collected public-comment/search datasets on disk, increasing local data exposure risk to other users, processes, backups, or support workflows.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.