小红书内容创作
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only Xiaohongshu content-writing skill with no code, credentials, account access, persistence, or publishing automation.
Safe to install from a security perspective. Users should still review generated posts for accuracy, brand fit, platform compliance, and proper AI-generated-content labeling 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
66/66 vendors flagged this skill as clean.