Security audit

抖音搜索关键词

Security checks across malware telemetry and agentic risk

Overview

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

Install only if you are comfortable sending Douyin search terms, Douyin links or IDs, and your GUAIKEI_API_TOKEN to guaikei.com. Use explicit Douyin-related prompts to avoid accidental routing, keep the token out of shared logs or screenshots, and delete the skill's local logs if collected public data or research activity should not persist on disk.

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: 78% confidence
Finding: The trigger list contains broad terms such as '数据分析', '短视频运营', '舆情监控', and '热点追踪' that can match general business or content-analysis requests outside a narrowly scoped Douyin lookup. Over-broad routing can cause the agent to invoke this skill unexpectedly and send user-supplied keywords, links, or analysis targets to the third-party API, increasing unnecessary data exposure and mis-execution risk.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The README states that JSON logs are automatically written to a local logs directory, including search terms, video/comment targets, and derived identifiers, but it does not clearly warn users that potentially sensitive research activity and collected public data will be persisted on disk. This creates a privacy and data-handling risk because users may unknowingly retain scraped content and operational metadata that can later be exposed through backups, shared workspaces, or local compromise.

Missing User Warnings

Medium

Confidence: 80% confidence
Finding: The README instructs users to obtain and set GUAIKEI_API_TOKEN for operation but does not explicitly warn that the token is used to authenticate to an external third-party service and should be treated as a secret. This omission increases the chance of credential mishandling, accidental disclosure in shell history or screenshots, and uninformed transmission of access credentials to a remote provider.

Vague Triggers

Medium

Confidence: 85% confidence
Finding: The natural-language mapping accepts very broad triggers such as '搜索', '搜一下', and '找 + 关键词', which are common phrases in ordinary conversation and can cause accidental invocation of the skill when a user did not intend to query Douyin. In an agent environment, overly generic triggers raise the risk of unintended external requests, unnecessary data collection, and surprising execution based on ambiguous prompts.

Vague Triggers

Medium

Confidence: 82% confidence
Finding: The intent-recognition rules use generic terms like '热搜', '热点', '榜单', and '今天什么火' without requiring a Douyin-specific context, so unrelated requests about general trends could be misrouted to this skill. Because the skill performs external data retrieval and logging, ambiguous activation can lead to unintended network calls and collection of third-party content beyond the user's actual request.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.