Security audit
XiaoHongShu
Security checks across malware telemetry and agentic risk
Overview
This skill is a simple Xiaohongshu content-writing helper with no evidence of hidden data collection, credential access, destructive behavior, or deceptive runtime instructions.
This appears safe to install for Xiaohongshu content drafting. Because it is an npm-based package, review npm install behavior in your environment, especially the install lifecycle script and the external Google AI SDK dependency, before installing in a sensitive workspace.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.