Security audit
Xiaohongshu Writer
Security checks across malware telemetry and agentic risk
Overview
This is a writing-template skill for Xiaohongshu posts and does not request code execution, credentials, file access, or account control.
Safe to install as a writing aid. Users should still review generated public posts for accuracy, platform rules, advertising disclosures, and appropriateness before publishing.
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
63/63 vendors flagged this skill as clean.