小红书算法优化师
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed Xiaohongshu content-optimization skill made of markdown guidance only, with no evidence of hidden execution, data access, or persistence.
This appears safe to install from an agentic-security perspective. Users should still treat its marketing and platform-growth advice as content guidance, review generated claims for accuracy and platform policy compliance, and avoid using it to create misleading or regulated-content promotions.
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.