guaikei-douyin-comprehensive-feed-grabber

• Outcome: Review
• Latest audit: Aug 24, 2026 · 4:26 AM UTC
• Version: 1.0.0

Overview

The skill is a coherent Douyin public-data research tool, but it needs Review because it can trigger on broad non-Douyin requests and automatically saves large scraped datasets locally.

Review before installing. Use this only when Douyin public-data collection is intended, keep the GUAIKEI_API_TOKEN private, and assume queries, Douyin URLs, and results are sent to guaikei.com. Check or delete the generated logs because they may contain public user comments and profile identifiers, and avoid collecting or retaining more data than needed.

SkillSpector

Vulnerability Patterns

• 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
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (13)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 85% confidence
• Finding: The skill requires access to an environment variable (`GUAIKEI_API_TOKEN`) but does not explicitly declare that capability in a permissions model. Hidden or undocumented secret access weakens reviewability and least-privilege controls, making it easier for a skill to consume sensitive runtime data without clear operator awareness.

Description-Behavior Mismatch

Medium

• Confidence: 98% confidence
• Finding: The document states the skill does not write to the filesystem except logs, but later says it automatically saves output files under `logs/`. This contradiction can mislead reviewers and users about data persistence, and stored outputs may contain scraped content, query terms, or other sensitive research artifacts that remain on disk unexpectedly.

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 that it is not for downloading videos. This mismatch can enable downstream agents or users to use the skill for prohibited content retrieval, expanding the capability beyond the declared safety boundary and increasing policy/compliance risk.

Description-Behavior Mismatch

Medium

• Confidence: 93% confidence
• Finding: The CLI silently persists fetched Douyin post results to a local JSON file after completing what is presented as a read-only lookup operation. This creates an undeclared data-retention side effect: scraped public data, potentially including profile and engagement metadata, is stored on disk where other local users, processes, backups, or later tooling may access it unexpectedly.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The skill description says it should be used even when the user does not mention Douyin, which broadens activation beyond explicit user intent. Over-triggering a networked data-collection skill can cause unintended third-party queries, unnecessary token use, and collection of external data not clearly requested by the user.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The generalized trigger guidance says broad multi-step research tasks should invoke the skill even when the platform is not specified. In context, this increases the chance of silent scope expansion during workflows, causing the agent to fetch external platform data without a clear, bounded user instruction.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The natural-language trigger mappings include generic phrases such as '搜索 / 搜一下 / 找' that can match ordinary user requests beyond a clearly scoped Douyin-data task. In an agent environment, this can cause unintended invocation of a scraping skill, leading to surprise data collection, unnecessary token usage, and actions the user did not specifically consent to.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The intent recognition rules prioritize broad terms like '热搜 / 热点 / 榜单 / 今天什么火' without requiring the user to mention Douyin or public-data retrieval. This makes accidental routing likely, especially in multi-skill assistants, and can trigger external data collection in response to vague conversational requests.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The README states that scraped data is automatically exported to local JSON logs, but it does not prominently warn that comments, profile data, and other public content may still contain personal or sensitive information. This increases the risk of unintended retention, internal sharing, or downstream misuse of collected personal data, especially in marketing and monitoring workflows.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The documentation explicitly supports collecting creator works and comment data from Douyin at significant scale, but provides no privacy, consent, retention, or terms-of-service guidance. In a scraping-oriented skill, that omission can normalize bulk collection of user-generated content and increase the risk of misuse, overcollection, or non-compliant handling of personal data.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The CLI writes fetched comment data to a local JSON file automatically, but this file contains potentially sensitive or regulated user-generated content and may persist on disk longer than the user expects. In shared environments, CI runners, or multi-user systems, silent persistence increases the risk of unintended disclosure through local access, backups, logs, or artifact collection.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: Writing results to a local JSON file without any user-facing warning is a transparency and privacy problem because users may reasonably expect a query tool to print results only to stdout. The hidden persistence can expose collected data through shared machines, shell history workflows, automated sync/backup tools, or subsequent processing pipelines that treat the file as intentional output.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: The CLI writes the full search output to a local JSON file named with user-derived content, but the user is not clearly warned that their queries and returned data will be persisted on disk. This creates a privacy and data-handling risk, especially on shared systems or automated environments where logs may be collected, retained, or exposed beyond the immediate execution context.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.