ClawHub
Back to skill

Security audit

guaikei-douyin-raw-to-structured-pipeline

Security checks across malware telemetry and agentic risk

Overview

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

Install only if you are comfortable sending Douyin search terms, links, and your GUAIKEI_API_TOKEN to guaikei.com, and with fetched public results being saved locally in the skill’s logs directory. Avoid using it for private, login-only, or restricted content, and clean up logs if the data is sensitive for your team.

SkillSpector

By NVIDIA
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 (4)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The natural-language trigger examples are broad enough to match common user phrasing such as '找一下', '热点', or '视频', which can cause the skill to activate outside its intended scope. In an agent setting, this increases the chance of misrouting ordinary requests into external data collection actions against Douyin, leading to unintended tool use and possible privacy/compliance issues.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The intent-recognition priority rules rely on ambiguous high-frequency words like '热搜', '搜索', '评论', '作品', and '博主' without sufficiently constraining them to Douyin-specific context. This can cause the agent to invoke the wrong capability or invoke this skill for unrelated requests, resulting in unauthorized external queries, incorrect data retrieval, and unsafe autonomous behavior.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The CLI writes fetched comment data to a local JSON file automatically after successful execution, but there is no explicit user-facing consent or warning before persisting the data. Because comment content may include personal data or sensitive business monitoring results, this can create an unexpected privacy and data-retention risk, especially on shared systems or in automated pipelines.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The CLI writes the full fetched results to a local JSON file automatically, without explicit user consent, output path control, or any warning that potentially sensitive scraped data will be persisted on disk. In this skill context, the data can include creator/content metadata at scale, so silent persistence increases the risk of unintended retention, disclosure to other local users/processes, or accidental inclusion in backups and source repositories.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.