ClawHub
Back to skill

Security audit

小红书数据洞察与竞品分析助手

Security checks across malware telemetry and agentic risk

Overview

This skill coherently provides user-directed Xiaohongshu public-data lookup through a disclosed third-party API, with local result logging that users should manage carefully.

Before installing, confirm you are comfortable sending Xiaohongshu keywords or links to Guaikei with your API token and having returned public posts/comments saved under the package logs directory. Use it only for lawful, terms-compliant analysis, avoid collecting more creator/comment data than needed, and delete or restrict logs when they are no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The skill explicitly supports searching, collecting, and analyzing public Xiaohongshu notes, posts, and comments, but the documentation lacks warnings about privacy expectations, platform terms, lawful basis for data use, retention, and downstream handling of scraped personal data. In this context, the danger is not code execution but enabling large-scale collection and analysis of user-generated content without safeguards, which can lead to privacy violations, policy noncompliance, and misuse of personal data.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The CLI writes fetched comment results to a local JSON file automatically, but this file contains potentially sensitive or regulated user-generated content and the behavior is not clearly surfaced as a privacy/storage warning in this file. In multi-user environments, shared workstations, CI runners, or agent sandboxes, persistent local storage can unintentionally expose collected data beyond the immediate command output.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The CLI sends the user-supplied note URL and retrieves remote data, then persists the full result set to a local JSON file via log.taskWrite without clearly warning the user that data will be transmitted to an external service and stored on disk. In this skill context, the returned data may include public note content and comments, but local persistence can still create privacy, compliance, or operational risk if users assume the tool is transient or run it in shared environments.

VirusTotal

50/50 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.