Ai Cli Architecture
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only AI CLI architecture guide and does not install code, run commands, or request credentials.
Reasonable to install as a reference guide. If you later build or install an implementation based on this architecture advice, review that separate code for filesystem access, credential handling, background execution, permission modes, and audit controls.
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
61/61 vendors flagged this skill as clean.