ClawHub
Back to skill

Security audit

guaikei-douyin-authors-scrape

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only Douyin public-data lookup tool that uses a disclosed third-party API and local result logs, with no evidence of hidden or destructive behavior.

Before installing, be aware that your Douyin search terms, target URLs or IDs, limits, and API token are sent to guaikei.com, and successful search/post/comment results are saved locally under the skill's logs directory. Use it only for public Douyin data you are allowed to analyze, and clear or protect the logs if the research is sensitive.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The natural-language trigger examples are broad enough to match common user phrasing such as '搜索', '找', or generic references to videos and trends, which can cause the skill to activate when the user did not explicitly intend to use this external data-scraping capability. In this context, unintended activation may send user-provided keywords or URLs to the tool and fetch external data, creating privacy, consent, and least-surprise issues.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The intent recognition rules prioritize broad keywords like '热搜', '搜索', '评论', '作品', and '视频' in ways that can overlap with ordinary discussion, making false-positive routing likely. Because this skill can perform external queries and data collection, ambiguous matching increases the chance of unintended scraping requests, unnecessary token use, and disclosure of user-supplied targets into logs or API calls.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README states that JSON logs are automatically generated and later clarifies they are stored under the local logs directory, but it does not prominently warn that fetched public data, comments, and search targets will be persisted to disk by default. This can expose sensitive research activity, monitored accounts, or scraped comment content to other local users, backups, or downstream systems without the operator's informed consent.

Static analysis

No suspicious patterns detected.