Security audit

guaikei-douyin-competitor-analysis

Security checks across malware telemetry and agentic risk

Overview

This is mostly a Douyin data-analysis tool, but users should review its automatic local data logging and download-capable media URL outputs before installing.

Install only if you are comfortable sending Douyin research queries and URLs to guaikei.com and having full result sets saved under the skill's local logs directory. Treat saved logs as potentially sensitive, especially for competitor research or comment/profile data, and avoid using the media URL fields for downloading unless you have the necessary rights and authorization.

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 (8)

Description-Behavior Mismatch

Medium

Confidence: 91% confidence
Finding: The schema explicitly documents `video_url` as including both playback and download addresses, which conflicts with the skill’s declared constraint that it is not for downloading videos. Exposing download-capable URLs in a supported response format can enable downstream consumers to use the skill for prohibited content acquisition, weakening policy boundaries and increasing misuse risk.

Description-Behavior Mismatch

Medium

Confidence: 88% confidence
Finding: The schema explicitly documents `play_addr` as both a playback address and a video download address, which conflicts with the skill’s stated restriction that it is not used for downloading videos. Even though this file is only a schema, exposing and normalizing a download field can enable downstream agents or integrators to use the skill for prohibited content retrieval, creating policy bypass and misuse risk.

Description-Behavior Mismatch

Medium

Confidence: 93% confidence
Finding: The CLI persists the full API response to a local JSON file after printing results, even though the skill is described as a query/analysis tool rather than a data-retention tool. This creates an undisclosed local data store containing fetched Douyin content and metadata, which can be exposed to other local users, backup systems, or later processes if the file permissions and retention policy are not controlled.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The description says the skill should be used even when the user is doing content research without explicitly naming Douyin, which broadens activation beyond clear user intent. That can cause the agent to invoke this skill for generic research requests and send user queries or URLs to an external third-party API unnecessarily, increasing data exposure and routing mistakes.

Vague Triggers

Low

Confidence: 73% confidence
Finding: The natural-language examples include broad phrases such as '帮我做抖音竞品分析' without requiring concrete inputs first. In an agent environment, loose trigger examples can make the skill over-match everyday requests, leading to premature invocation, unnecessary external API use, and confusion about whether the user intended this specific platform/tool.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The README explicitly states that collected Douyin data is automatically exported to local JSON logs, including comments and account-related data, but it does not give a prominent warning about the privacy and retention implications of storing this data on disk. Because comments, profile identifiers, and behavioral data may be sensitive or regulated, silent local persistence increases the risk of unintended disclosure through shared machines, backups, source control, or log collection tools.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: Sensitive or potentially proprietary API results are written to a local file without any user-facing warning, consent, or indication of retention. In a competitor-analysis skill, fetched datasets may include large-scale content intelligence that users reasonably expect to be ephemeral, so silent persistence increases confidentiality and compliance risk.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The CLI writes the full search output to a local JSON file using a filename derived from user-controlled input (`keyword`) and does so without an explicit opt-in or warning. In this skill’s context, search terms and returned results may contain sensitive business-intelligence or monitoring data, so silent persistence increases the risk of unintended local disclosure, retention, or later exfiltration by other processes/users on the host.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.