Security audit

guaikei-douyin-authors-for-benchmarking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, read-only Douyin public-data retrieval tool, with the main caution that it sends queries to a third-party API and automatically saves some result files locally.

Install only if you are comfortable sending Douyin search terms, URLs or IDs, requested limits, and your GUAIKEI_API_TOKEN to guaikei.com. Treat saved files in the skill logs directory as retained social-media datasets, especially for comments and author metadata, and delete or protect them when no longer needed.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The natural-language trigger examples are broad enough that an orchestrator could invoke this skill for vague requests like '抖音今天有什么热点' or '帮我做抖音竞品分析' without sufficient user confirmation. Because the skill sends user-provided queries and links to a third-party API, unintended invocation can cause unnecessary external data disclosure, surprise tool use, or execution against the wrong target.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The README explicitly promotes automatic JSON log generation for search, author, and comment collection, but it does not prominently warn that scraped public data will be stored locally and may contain sensitive or regulated personal data. This can lead users to unintentionally retain large datasets on disk, increasing privacy, compliance, and secondary exposure risk if logs are shared, synced, or left unprotected.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The README instructs users to obtain and set a private API token in an environment variable, but the warning about token security is brief and not prominent relative to the setup instructions. This increases the chance of accidental credential disclosure through shell history, screenshots, shared terminals, CI logs, or copied environment files, which could enable unauthorized API use.

Missing User Warnings

Low

Confidence: 93% confidence
Finding: The CLI writes fetched comment data to a local JSON file automatically, without obtaining explicit user consent or prominently warning that potentially sensitive or regulated data will be persisted on disk. In this skill context, the data being handled is scraped social-media comment content, which can create privacy, retention, and unintended disclosure risks if the file is later accessed by other users, backup systems, or logs.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The CLI writes the full retrieved post results to a local JSON file automatically after execution, without any indication in this file that the user explicitly opted into local persistence. Even though the data is described as public Douyin data, stored results may still contain sensitive operational research, account metadata, or comments, and can remain on disk longer than intended where other local users, processes, backups, or malware could access them.

Static analysis

No suspicious patterns detected.