guaikei-douyin-bulk-videos-fetch

• Outcome: Review
• Latest audit: Aug 21, 2026 · 1:48 AM UTC
• Version: 1.0.0

Overview

This skill mostly does what it says, but it handles API tokens and scraped Douyin data in ways users should review before installing.

Install only if you are comfortable sending Douyin keywords, profile/video URLs, requested limits, and your GUAIKEI_API_TOKEN to www.guaikei.com. Treat saved logs as potentially sensitive, especially comment exports with user identifiers, and delete them when no longer needed. Do not use the exposed media URLs for downloading or redistribution unless you have the rights and platform permission to do so.

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 (11)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 86% confidence
• Finding: The skill explicitly relies on the `GUAIKEI_API_TOKEN` environment variable, but the metadata shown in this file does not declare any corresponding permission or capability. That creates a transparency and review gap: operators may approve the skill without understanding it accesses secrets from the environment and sends authenticated requests to an external service.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 95% confidence
• Finding: The declared behavior centers on Douyin data retrieval, but the file also discloses local logging of query/result data and interaction with a third-party service (`www.guaikei.com`) for task creation/query. This mismatch is security-relevant because user requests, searched keywords, URLs, and fetched comment data may be persisted locally and transmitted off-platform without being clearly surfaced as part of the core behavior.

Description-Behavior Mismatch

Medium

• Confidence: 93% confidence
• Finding: The schema explicitly documents `video_url` as both playback and download addresses, which conflicts with the skill's stated restriction against download-oriented use. In this context, exposing download URLs can enable users or downstream agents to repurpose the skill for bulk media extraction, undermining policy boundaries and increasing abuse risk even if watermark removal is not explicitly implemented here.

Description-Behavior Mismatch

Medium

• Confidence: 91% confidence
• Finding: The schema explicitly documents `play_addr` as both a playback URL and a video download address, which conflicts with the skill's stated scope that it is not for downloading or watermark-removal. Even though this file is only a schema, exposing and normalizing a download-oriented field can enable downstream agents or users to misuse the skill for prohibited content retrieval and bypass product-policy boundaries.

Description-Behavior Mismatch

Medium

• Confidence: 89% confidence
• Finding: The CLI persists fetched Douyin post results to a local JSON file after completing the query, which expands behavior from transient fetching into data retention. This can expose scraped content, metadata, and potentially sensitive research targets to other local users, backup systems, or later unintended reuse, especially because the write occurs automatically without an explicit opt-in in this file.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill documents comment scraping and automatic JSON log storage, but it does not prominently warn users that fetched comments and query inputs may be retained locally and potentially include personal data or sensitive research targets. This lack of notice increases privacy and data-handling risk, especially for bulk collection and sentiment-analysis use cases.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The changelog explicitly adds bulk retrieval of competitor account content and video comments, but provides no mention of privacy safeguards, lawful-use boundaries, rate limiting, or data-handling constraints. In the context of a scraping/analytics skill targeting a social platform, this omission increases the likelihood of misuse for mass profiling, surveillance, or collection of personal data from comments and creator activity.

Missing User Warnings

Low

• Confidence: 82% confidence
• Finding: The GET request places the token and keyword into URL query parameters. Query strings are commonly exposed in server logs, reverse proxies, browser history, monitoring tools, and referrer-like telemetry, so putting credentials in the URL increases accidental disclosure risk even when transport is encrypted.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The CLI persists fetched comment data to a local JSON file automatically after successful execution, but the code does not provide a clear warning, consent prompt, or option to disable storage. Since comment data can contain personal data, usernames, or sensitive research material, silent persistence increases the risk of unintended local exposure, retention, and secondary access by other users/processes on the host.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: Result data is written to a local JSON file without any warning or consent prompt in this file, creating undisclosed local data storage. In a content-research workflow, users may expect a fetch/query action only; silent persistence increases privacy, compliance, and operational risk if the data contains sensitive account targets, comments, or research artifacts.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: The CLI writes full search results to a local file automatically, with a filename derived from user-supplied keyword content, but provides no explicit notice or consent at the write site. In this skill's context, search results may contain sensitive research terms or scraped content metadata, so silent persistence increases privacy and data-handling risk on shared systems or agent environments.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.