Create Cli
Security checks across malware telemetry and agentic risk
Overview
This skill is an instruction-only aid for designing command-line interfaces and does not ask to run code, access credentials, or change the system.
This appears safe to install as a CLI design helper. It may influence the CLI specs your agent writes, so review any generated destructive-operation flags, confirmation behavior, and config conventions before implementation, but the skill itself does not perform those actions.
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.