Client Onboarding Agent
Security checks across malware telemetry and agentic risk
Overview
This is a non-executable client onboarding framework that asks for business context but does not install code, request credentials, or hide behavior.
Install this only if you want a structured client-discovery workflow for AI automation projects. When using it, get client consent before screen sharing, do not collect passwords or unnecessary regulated data, store onboarding notes and generated plans confidentially, and keep financial, legal, compliance, and other high-impact automations under human approval unless separately scoped and tested.
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
66/66 vendors flagged this skill as clean.