Shell Ai
Security checks across malware telemetry and agentic risk
Overview
This is a simple Shell AI reference skill that only prints local help documentation and does not show credential use, network access, persistence, or file mutation.
This appears safe to install if you want a local reference command. Be aware that the content is generic guidance and the script has a minor version mismatch, but there is no evidence of sensitive access, network calls, persistence, or harmful behavior.
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
46/46 vendors flagged this skill as clean.
