Security audit

guaikei-xhs-explorer

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu public-data research tool that uses a third-party API token and saves retrieved results locally for later analysis.

Install only if you are comfortable sending Xiaohongshu keywords or URLs and your GUAIKEI_API_TOKEN to guaikei.com. Review or delete the generated logs directory when handling sensitive competitive research, because retrieved public content and query context are saved locally by default.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (6)

Description-Behavior Mismatch

Medium

Confidence: 91% confidence
Finding: The CLI persists fetched creator-post results to a local JSON file via log.taskWrite, but the user-facing description and help text do not clearly disclose that data will be stored on disk. Silent persistence can expose scraped data, query targets, and operational metadata to other local users, backups, or later unintended reuse, especially in shared or automated environments.

Description-Behavior Mismatch

Medium

Confidence: 92% confidence
Finding: The CLI writes full search results to a local file even though its described purpose is only to retrieve/search public Xiaohongshu content. This creates an undisclosed data persistence channel that can retain potentially sensitive research activity, queried keywords, and scraped content on disk, increasing privacy and data-handling risk beyond what users would reasonably expect.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The README states that all task results are automatically saved to the `logs/` directory, but it does not clearly warn users that collected third-party content, URLs, keywords, and comments may be persisted locally by default. In a data-scraping/analytics skill, silent disk persistence increases the risk of unintended retention, disclosure, or misuse of potentially sensitive business research data and public-user content, especially on shared machines or CI/server environments.

Missing User Warnings

Low

Confidence: 78% confidence
Finding: The CLI persists the full result payload to a local JSON file without explicit user consent or a clear warning in the help output. Because this skill handles note details and comments, it may store scraped content and metadata on disk unexpectedly, creating privacy and data-handling risk on shared systems or in automated environments.

Missing User Warnings

Low

Confidence: 93% confidence
Finding: The CLI writes fetched results to a local JSON file without an explicit warning or consent mechanism. Even though the data appears to be public Xiaohongshu content, undeclared persistence can still create privacy, compliance, and operational risk by leaving data artifacts on disk unexpectedly.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: Search results are silently saved to a local file without explicit user confirmation or a visible warning. Even if the source data is public, the saved file can expose user interests, investigative queries, or accumulated scraped datasets to other local users, backup systems, or unintended workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.