ClawHub
Back to skill

Security audit

xiaohongshu-matrix-factory

Security checks across malware telemetry and agentic risk

Overview

This is a text-only Xiaohongshu content-generation skill with no code, credential access, persistence, or direct publishing behavior.

Reasonable to install as a content generator. Review generated posts for accuracy, advertising disclosure, platform-policy compliance, and intellectual-property issues. Only use browser automation to publish if you intentionally want the agent to act on the correct social account.

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
93% confidence
Finding
The trigger phrases are broad enough to activate on ordinary, generic content-writing requests, which can cause the skill to take over conversations outside its intended scope. In this skill, that matters because it steers users toward large-scale social-media content generation and browser-automation-adjacent workflows, increasing the chance of unintended invocation and misuse.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.