ClawHub
Back to skill

Security audit

xhs-word-cloud

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu public-data lookup tool, with the main caution that it sends queries and URLs to a third-party API and saves successful results locally.

Install only if you are comfortable using GuAikei as the backend for Xiaohongshu data requests. Avoid pasting sensitive/private URLs, protect the GUAIKEI_API_TOKEN, and periodically delete the skill's logs directory if retained search results, profile URLs, comments, or request metadata should not remain on disk.

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 (4)

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The CLI writes full search output to a local JSON file with a filename derived from user input. Even though the skill is a search/analytics tool, silent persistence increases data exposure risk by leaving potentially sensitive query terms and retrieved content on disk, where other local users, backup systems, or later processes may access it.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The CLI persists the full task output, which likely includes fetched note details and comments, to a local JSON file without clear consent or retention controls. This creates a privacy and data-handling risk because scraped public content may still be sensitive in aggregate, and local files can be unintentionally exposed, shared, or retained longer than intended.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The CLI sends a user-supplied Xiaohongshu profile URL together with the configured API token to an external backend, but the code does not clearly disclose that this data will be transmitted off-host at execution time. In a data-collection skill, external transmission is expected, but the lack of explicit notice or consent can still create privacy and data-handling risk, especially if users paste sensitive or private tracking URLs.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill automatically writes the collected results to a local JSON file without asking the user or prominently warning that data will be persisted on disk. This is lower severity because local result storage is common for CLI tooling, but it can still expose scraped data, metadata, or operational traces to other local users, backups, or downstream processes.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.