智美人AI实战课
Security checks across malware telemetry and agentic risk
Overview
This is a simple course-outline skill that does not ask the agent to run code, access accounts, or handle private data.
This appears safe as a course reference. Review any companion skills named by the course separately before installing them, since they are not included in this artifact.
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.