Security audit

douyin-detail

Security checks across malware telemetry and agentic risk

Overview

This skill coherently fetches public Douyin analytics data through a disclosed third-party API, with local JSON logging that users should manage carefully.

Install only if you are comfortable sending Douyin query terms, public links or IDs, and your GUAIKEI_API_TOKEN to guaikei.com. Review and delete the skill's local logs when they contain comments, author metadata, keywords, or business research you do not want retained.

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: 94% confidence
Finding: The changelog documents capabilities beyond the declared skill scope, including keyword search, trending-topic queries, bulk scraping of an author's published works, and comment collection. This kind of scope drift is dangerous because it can bypass user and platform expectations, expand data collection beyond the reviewed purpose, and enable higher-risk scraping or surveillance workflows that were not clearly disclosed in the skill metadata.

Description-Behavior Mismatch

Medium

Confidence: 89% confidence
Finding: The CLI persists fetched comment data to a local JSON file after completing its main operation, which creates an additional data sink beyond simply displaying or returning analytics results. Because there is no explicit user consent, opt-in flag, retention control, or data minimization, potentially sensitive scraped content can remain on disk unintentionally and be exposed to other local users, backup systems, or later compromise.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The README prominently advertises bulk collection and export of videos, author data, comments, and hot-list data, but it does not present a clear privacy warning about storing that scraped public data into local JSON logs. Even if the data is public, comments and account/activity data can still contain personal information, and silent local retention/export increases the risk of misuse, over-collection, and downstream disclosure.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The natural-language trigger mappings use broad phrases such as common conversational requests for searching, checking comments, or viewing works, which can overlap with ordinary user speech and cause unintended activation. In a data-collection skill, ambiguous routing is risky because it can trigger scraping or export operations the user did not clearly authorize, leading to unnecessary collection of third-party data and local persistence in logs.

Missing User Warnings

Low

Confidence: 84% confidence
Finding: The code silently writes comment results to a local file without clearly informing the user at runtime, which can violate user expectations and lead to accidental storage of collected content. In a data-collection skill, hidden persistence increases privacy and operational risk even if the file is stored locally and named predictably.

Missing User Warnings

Medium

Confidence: 80% confidence
Finding: The tool writes retrieved post data to a local JSON file automatically, without explicit user notice at execution time or a consent/opt-in control. In analytics contexts, fetched data may include sensitive business research, scraped content, or metadata that remains on disk longer than intended and can be accessed by other local users, backup systems, or downstream processes.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The CLI writes full search output, including the queried keyword and returned content data, to a local JSON file without explicit user notice or consent. This can expose sensitive research topics or collected platform data to other local users, backups, or later unintended disclosure, especially on shared systems.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.