ClawHub
Back to skill

Security audit

xhs-strategy-scan

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu public-data research tool that sends user-provided search terms or links to its documented API and saves returned results locally for later analysis.

Install only if you are comfortable sending Xiaohongshu keywords, note/profile URLs, and your GUAIKEI_API_TOKEN to www.guaikei.com. Review or clean the logs directory if the searches, URLs, comments, or profile data are sensitive to your work, and use the tool only for public data in line with Xiaohongshu and applicable policy requirements.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The CLI writes the full comment-task output to a local JSON file without any explicit notice, consent, or control in this file. Because the output may include scraped public comments, note metadata, or other potentially sensitive operational data, this creates an undisclosed local data-retention channel that can expose data to other local users, backups, or later misuse.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The script sends the user-supplied note URL and comment limit to external APIs to create and fetch a comment task, but the file does not clearly disclose this transmission at the point of use. In a data-collection tool, undisclosed outbound transmission can surprise users, leak research targets or usage patterns, and create privacy/compliance issues even if the destination is part of intended functionality.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The CLI prints and persists user-supplied note URLs and the full retrieved detail payload, which may include sensitive metadata, comments, or identifiers from public content that users did not intend to store locally or expose in terminal logs. In this skill context, bulk collection and analysis of social content makes silent logging more risky because outputs may be captured by shell history, CI logs, shared terminals, or local files without any explicit privacy warning or redaction.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The CLI writes the full search output, including the user-supplied keyword and all returned results, to a local JSON file without explicit disclosure or opt-in. In this skill context, the data is market-intelligence content from a third-party platform, so silent persistence can expose sensitive research terms, collected profile/content data, or operational history to other local users, backups, or downstream tooling.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.