Security audit

guaikei-douyin-data-stream

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly aligned with Douyin public-data analytics, but it automatically sends broad prompts to an external service and persists collected data locally without clear retention controls.

Install only if you are comfortable sending Douyin search terms, account/video targets, and the Guaikei API token to www.guaikei.com. Treat generated logs as sensitive business data, clean them up regularly, and confirm before using the skill for ambiguous short-video or hot-topic requests.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 83% confidence
Finding: The skill declares no explicit permissions, yet it requires access to the environment for `GUAIKEI_API_TOKEN`. This creates a transparency and least-privilege problem: reviewers and users are not clearly informed that secret-bearing environment access is required, which can lead to unexpected secret exposure or overly broad runtime trust.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger logic is intentionally broad and explicitly allows activation even when 'Douyin' is not mentioned, such as generic requests to 'check' short-video content or hot topics. This can cause over-invocation on ambiguous user requests, sending user queries to an external data service without sufficiently specific user intent or platform scoping.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill states that logs are automatically saved to `logs/` and include keywords/parameters in filenames, but the user-facing description does not prominently warn that their queries may be retained on disk. This is a privacy and data-retention issue because user inputs may contain sensitive business topics, account URLs, or other identifiable data that gets stored unexpectedly.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill documents automatic export of collected Douyin data to local log files and later specifies storage in a logs directory, but it does not prominently warn users that comments, account data, and search results may persist on disk. This creates a privacy and data-handling risk because potentially sensitive or regulated scraped content could be retained unintentionally, exposed to other local users, or included in backups and downstream processing.

Ssd 3

Medium

Confidence: 97% confidence
Finding: Automatically archiving logs using user-provided keywords and parameters in filenames creates avoidable data leakage and retention risk. Sensitive search terms, URLs, or investigation targets may be exposed through filesystem metadata, log listings, backups, or shared environments, even if the command output itself is otherwise controlled.

Static analysis

No suspicious patterns detected.