AI-CLI Design
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill about designing AI-friendly CLI tools, with no executable code or hidden data access.
Safe to install as a CLI design guide. When applying its recommendations to real tools, treat --yes and --no-input carefully for delete, account-changing, or business-impacting commands, and prefer dry-run or preview behavior where possible.
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
65/65 vendors flagged this skill as clean.