横纵研究工作台
Security checks across malware telemetry and agentic risk
Overview
This is a coherent research-report skill with an optional local Markdown-to-PDF helper and no evidence of hidden data access, persistence, or exfiltration.
Install this if you want a Chinese-first structured research workflow. Be aware that generating PDFs may require local Python dependencies, and specify a different output language when invoking the skill if Chinese is not desired.
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
67/67 vendors flagged this skill as clean.