Back to skill

Security audit

Auto Redbook Content

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu content-fetching and rewrite-prompt helper that writes local output files and shows no hidden or destructive behavior.

Install this if you want a local helper for Xiaohongshu-style rewrite prompts. Be aware that real fetching may depend on an external Xiaohongshu MCP tool, and fetched content plus prompts remain in local output JSON files until you delete them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.