ClawHub
Back to skill

Security audit

Xiaohongshu Analyzer

Security checks across malware telemetry and agentic risk

Overview

The skill appears to provide Xiaohongshu analysis/scraping help, and the only flagged issue is broad activation wording rather than hidden or unsafe behavior.

Install only if you want an agent to help analyze Xiaohongshu content and keywords. Because the trigger wording may be broad, be explicit when you want this skill used, and review any scraping or analysis actions before running them against third-party content.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill exposes broad natural-language trigger examples without clear activation boundaries, which can cause overbroad invocation or unintended use in adjacent contexts. In an agent setting, vague triggers increase the chance that unrelated user requests containing Xiaohongshu URLs, competitor analysis, or keyword research language will activate scraping/analysis behaviors unexpectedly.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.