Security audit

guaikei-xhs-search

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Xiaohongshu public-data lookup skill, with expected third-party API use and local result logging that users should understand before installing.

Install this only if you are comfortable sending Xiaohongshu keywords or URLs and your GUAIKEI API token to guaikei.com, and with returned public-data results being saved locally under logs. Review or delete those log files when the research may be sensitive or used on shared systems.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Description-Behavior Mismatch

Medium

Confidence: 90% confidence
Finding: The CLI writes the full fetched creator-post response to a local JSON file, which can unintentionally retain scraped public data, metadata, and possibly operational context longer than the user expects. Even if the source data is public, silent persistence increases privacy, compliance, and secondary-exposure risk on shared machines or in automated environments.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The README states that all task results are automatically saved to the `logs/` directory, but it does not clearly warn users that searched keywords, queried links, and scraped public-content results will be persisted to local disk. In this skill’s context, that can create unintended retention of potentially sensitive business intelligence, research targets, campaign terms, or scraped content, increasing the risk of local disclosure, accidental sharing, or compliance issues.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The CLI writes the full comment task output to a local JSON file, which can persist potentially sensitive or regulated content such as comment text, note URLs, and metadata without an explicit warning or opt-in. In a data-collection tool, this increases the risk of unintended retention, local exposure to other users/processes, and compliance/privacy issues if operators assume the data is only printed transiently.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The tool sends the user-supplied note URL and API token to an external service to create and retrieve comment tasks, but the code does not provide a clear runtime disclosure that this data is transmitted off-host. In the context of a scraping/analytics skill, users may reasonably expect network activity, but lack of explicit notice can still create privacy, consent, and operational risk, especially when analyzing third-party content or using sensitive tokens.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The CLI writes the full search output, including user-supplied keyword, timestamps, metadata, and returned results, to a local JSON file without any visible consent, opt-in, or disclosure at the point of execution. In a data-collection skill focused on scraping/searching public social content, silent persistence increases privacy, retention, and multi-user leakage risk, especially on shared hosts or automation runners where local artifacts may be accessible to others.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.