Security audit

抖音搜索关键词

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Douyin public-data retrieval tool that uses a third-party API and saves JSON logs locally, with no evidence of hidden exfiltration or destructive behavior.

Install only if you are comfortable sending Douyin search terms, profile/video URLs, limits, and your GUAIKEI_API_TOKEN to the guaikei.com API. Review or delete the generated logs if the collected public comments or account data are sensitive for your workflow.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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)

Description-Behavior Mismatch

Medium

Confidence: 88% confidence
Finding: The CLI silently persists fetched comment data to a local JSON file after printing results, which expands behavior from transient retrieval into local storage of potentially sensitive or regulated data. Even though the data is described as public Douyin content, comments can contain personal information or operationally sensitive research data, and undisclosed disk writes increase privacy, retention, and data-handling risk.

Description-Behavior Mismatch

Medium

Confidence: 89% confidence
Finding: The CLI persists fetched Douyin results to a local JSON file without disclosing this behavior in the help text or obtaining explicit user consent. Even if the source data is nominally public, the stored output may contain aggregated content, account identifiers, or comments that create privacy, retention, and data-handling risks beyond simple on-screen retrieval.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The tool writes full comment results to a local JSON file without warning in help text or an explicit user consent mechanism. Silent persistence can surprise users, leak collected datasets to other local users/processes, and create unintended retention of scraped content that may include personal data.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The tool transmits user-supplied Douyin URLs and query parameters to a remote API service, but the CLI does not provide a clear user-facing notice that input will be sent off-host. This can surprise users and expose sensitive investigative targets, internal workflow context, or monitored accounts to a third-party service.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The CLI writes fetched results to a local JSON file automatically, without prior disclosure or an explicit save option. This creates unexpected local persistence of potentially sensitive aggregated data, increasing the risk of unauthorized access, accidental sharing, or retention beyond the user's intent.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.