Security audit
Small Red Book
Security checks across malware telemetry and agentic risk
Overview
This is a simple content-writing skill for Xiaohongshu-style product notes and does not request code execution, data access, credentials, persistence, or network activity.
Safe to install from a security perspective. Review generated posts for advertising disclosure, platform rules, and factual product claims 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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.